- Date & Time: Tuesday, October 31, 2023; 2:00 PM
Speaker: Tanmay Gupta, Allen Institute for Artificial Intelligence
MERL Host: Moitreya Chatterjee
Research Areas: Artificial Intelligence, Computer Vision, Machine Learning
Abstract 
Building General Purpose Vision Systems (GPVs) that can perform a huge variety of tasks has been a long-standing goal for the computer vision community. However, end-to-end training of these systems to handle different modalities and tasks has proven to be extremely challenging. In this talk, I will describe a lucrative neuro-symbolic alternative to the common end-to-end learning paradigm called Visual Programming. Visual Programming is a general framework that leverages the code-generation abilities of LLMs, existing neural models, and non-differentiable programs to enable powerful applications. Some of these applications continue to remain elusive for the current generation of end-to-end trained GPVs.
-
- Date: January 23, 2023 - November 4, 2023
Where: International Symposium of Music Information Retrieval (ISMR)
MERL Contacts: Jonathan Le Roux; Gordon Wichern
Research Areas: Artificial Intelligence, Machine Learning, Speech & Audio
Brief - MERL Speech & Audio team members Gordon Wichern and Jonathan Le Roux co-organized the 2023 Sound Demixing Challenge along with researchers from Sony, Moises AI, Audioshake, and Meta.
The SDX2023 Challenge was hosted on the AI Crowd platform and had a prize pool of $42,000 distributed to the winning teams across two tracks: Music Demixing and Cinematic Sound Demixing. A unique aspect of this challenge was the ability to test the audio source separation models developed by challenge participants on non-public songs from Sony Music Entertainment Japan for the music demixing track, and movie soundtracks from Sony Pictures for the cinematic sound demixing track. The challenge ran from January 23rd to May 1st, 2023, and had 884 participants distributed across 68 teams submitting 2828 source separation models. The winners will be announced at the SDX2023 Workshop, which will take place as a satellite event at the International Symposium of Music Information Retrieval (ISMR) in Milan, Italy on November 4, 2023.
MERL’s contribution to SDX2023 focused mainly on the cinematic demixing track. In addition to sponsoring the prizes awarded to the winning teams for that track, the baseline system and initial training data were MERL’s Cocktail Fork separation model and Divide and Remaster dataset, respectively. MERL researchers also contributed to a Town Hall kicking off the challenge, co-authored a scientific paper describing the challenge outcomes, and co-organized the SDX2023 Workshop.
-
- Date: October 2, 2023 - October 6, 2023
Where: Paris/France
MERL Contacts: Moitreya Chatterjee; Anoop Cherian; Michael J. Jones; Toshiaki Koike-Akino; Suhas Lohit; Tim K. Marks; Pedro Miraldo; Kuan-Chuan Peng; Ye Wang
Research Areas: Artificial Intelligence, Computer Vision, Machine Learning
Brief - MERL researchers are presenting 4 papers and organizing the VLAR-SMART-101 workshop at the ICCV 2023 conference, which will be held in Paris, France October 2-6. ICCV is one of the most prestigious and competitive international conferences in computer vision. Details are provided below.
1. Conference paper: “Steered Diffusion: A Generalized Framework for Plug-and-Play Conditional Image Synthesis,” by Nithin Gopalakrishnan Nair, Anoop Cherian, Suhas Lohit, Ye Wang, Toshiaki Koike-Akino, Vishal Patel, and Tim K. Marks
Conditional generative models typically demand large annotated training sets to achieve high-quality synthesis. As a result, there has been significant interest in plug-and-play generation, i.e., using a pre-defined model to guide the generative process. In this paper, we introduce Steered Diffusion, a generalized framework for fine-grained photorealistic zero-shot conditional image generation using a diffusion model trained for unconditional generation. The key idea is to steer the image generation of the diffusion model during inference via designing a loss using a pre-trained inverse model that characterizes the conditional task. Our model shows clear qualitative and quantitative improvements over state-of-the-art diffusion-based plug-and-play models, while adding negligible computational cost.
2. Conference paper: "BANSAC: A dynamic BAyesian Network for adaptive SAmple Consensus," by Valter Piedade and Pedro Miraldo
We derive a dynamic Bayesian network that updates individual data points' inlier scores while iterating RANSAC. At each iteration, we apply weighted sampling using the updated scores. Our method works with or without prior data point scorings. In addition, we use the updated inlier/outlier scoring for deriving a new stopping criterion for the RANSAC loop. Our method outperforms the baselines in accuracy while needing less computational time.
3. Conference paper: "Robust Frame-to-Frame Camera Rotation Estimation in Crowded Scenes," by Fabien Delattre, David Dirnfeld, Phat Nguyen, Stephen Scarano, Michael J. Jones, Pedro Miraldo, and Erik Learned-Miller
We present a novel approach to estimating camera rotation in crowded, real-world scenes captured using a handheld monocular video camera. Our method uses a novel generalization of the Hough transform on SO3 to efficiently find the camera rotation most compatible with the optical flow. Because the setting is not addressed well by other data sets, we provide a new dataset and benchmark, with high-accuracy and rigorously annotated ground truth on 17 video sequences. Our method is more accurate by almost 40 percent than the next best method.
4. Workshop paper: "Tensor Factorization for Leveraging Cross-Modal Knowledge in Data-Constrained Infrared Object Detection" by Manish Sharma*, Moitreya Chatterjee*, Kuan-Chuan Peng, Suhas Lohit, and Michael Jones
While state-of-the-art object detection methods for RGB images have reached some level of maturity, the same is not true for Infrared (IR) images. The primary bottleneck towards bridging this gap is the lack of sufficient labeled training data in the IR images. Towards addressing this issue, we present TensorFact, a novel tensor decomposition method which splits the convolution kernels of a CNN into low-rank factor matrices with fewer parameters. This compressed network is first pre-trained on RGB images and then augmented with only a few parameters. This augmented network is then trained on IR images, while freezing the weights trained on RGB. This prevents it from over-fitting, allowing it to generalize better. Experiments show that our method outperforms state-of-the-art.
5. “Vision-and-Language Algorithmic Reasoning (VLAR) Workshop and SMART-101 Challenge” by Anoop Cherian, Kuan-Chuan Peng, Suhas Lohit, Tim K. Marks, Ram Ramrakhya, Honglu Zhou, Kevin A. Smith, Joanna Matthiesen, and Joshua B. Tenenbaum
MERL researchers along with researchers from MIT, GeorgiaTech, Math Kangaroo USA, and Rutgers University are jointly organizing a workshop on vision-and-language algorithmic reasoning at ICCV 2023 and conducting a challenge based on the SMART-101 puzzles described in the paper: Are Deep Neural Networks SMARTer than Second Graders?. A focus of this workshop is to bring together outstanding faculty/researchers working at the intersections of vision, language, and cognition to provide their opinions on the recent breakthroughs in large language models and artificial general intelligence, as well as showcase their cutting edge research that could inspire the audience to search for the missing pieces in our quest towards solving the puzzle of artificial intelligence.
Workshop link: https://wvlar.github.io/iccv23/
-
- Date & Time: Thursday, September 28, 2023; 12:00 PM
Speaker: Komei Sugiura, Keio University
MERL Host: Chiori Hori
Research Areas: Artificial Intelligence, Machine Learning, Robotics, Speech & Audio
Abstract 
Recent advances in multimodal models that fuse vision and language are revolutionizing robotics. In this lecture, I will begin by introducing recent multimodal foundational models and their applications in robotics. The second topic of this talk will address our recent work on multimodal language processing in robotics. The shortage of home care workers has become a pressing societal issue, and the use of domestic service robots (DSRs) to assist individuals with disabilities is seen as a possible solution. I will present our work on DSRs that are capable of open-vocabulary mobile manipulation, referring expression comprehension and segmentation models for everyday objects, and future captioning methods for cooking videos and DSRs.
-
- Date: August 25, 2023
Awarded to: Alberto Dalla Libera, Niccolo' Turcato, Giulio Giacomuzzo, Ruggero Carli, Diego Romeres
MERL Contact: Diego Romeres
Research Areas: Artificial Intelligence, Machine Learning, Robotics
Brief - A joint team consisting of members of University of Padua and MERL ranked 1st in the IJCAI2023 Challenge "Al Olympics With RealAlGym: Is Al Ready for Athletic Intelligence in the Real World?". The team was composed by MERL researcher Diego Romeres and a team from University Padua (UniPD) consisting of Alberto Dalla Libera, Ph.D., Ph.D. Candidates: Niccolò Turcato, Giulio Giacomuzzo and Prof. Ruggero Carli from University of Padua.
The International Joint Conference on Artificial Intelligence (IJCAI) is a premier gathering for AI researchers and organizes several competitions. This year the competition CC7 "AI Olympics With RealAIGym: Is AI Ready for Athletic Intelligence in the Real World?" consisted of two stages: simulation and real-robot experiments on two under-actuated robotic systems. The two robotics systems were treated as separate tracks and one final winner was selected for each track based on specific performance criteria in the control tasks.
The UniPD-MERL team competed and won in both tracks. The team's system made strong use of a Model-based Reinforcement Learning algorithm called (MC-PILCO) that we recently published in the journal IEEE Transaction on Robotics.
-
- Date: July 11, 2023
Where: Daegu, Korea
MERL Contacts: Siddarth Jain; Devesh K. Jha; Arvind Raghunathan
Research Areas: Artificial Intelligence, Machine Learning, Robotics
Brief - MERL researchers presented 3 papers at the 19th edition of Robotics:Science and Systems Conference in Daegu, Korea. RSS is the flagship conference of the RSS foundation and is run as a single track conference presenting a limited number of high-quality papers. This year the main conference had a total of 112 papers presented. MERL researchers presented 2 papers in the main conference on planning and perception for dexterous manipulation. Another paper was presented in a workshop of learning for dexterous manipulation. More details can be found here https://roboticsconference.org.
-
- Date: June 9, 2023
Awarded to: Darius Petermann, Gordon Wichern, Aswin Subramanian, Jonathan Le Roux
MERL Contacts: Jonathan Le Roux; Gordon Wichern
Research Areas: Artificial Intelligence, Machine Learning, Speech & Audio
Brief - Former MERL intern Darius Petermann (Ph.D. Candidate at Indiana University) has received a Best Student Paper Award at the 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2023) for the paper "Hyperbolic Audio Source Separation", co-authored with MERL researchers Gordon Wichern and Jonathan Le Roux, and former MERL researcher Aswin Subramanian. The paper presents work performed during Darius's internship at MERL in the summer 2022. The paper introduces a framework for audio source separation using embeddings on a hyperbolic manifold that compactly represent the hierarchical relationship between sound sources and time-frequency features. Additionally, the code associated with the paper is publicly available at https://github.com/merlresearch/hyper-unmix.
ICASSP is the flagship conference of the IEEE Signal Processing Society (SPS). ICASSP 2023 was held in the Greek island of Rhodes from June 04 to June 10, 2023, and it was the largest ICASSP in history, with more than 4000 participants, over 6128 submitted papers and 2709 accepted papers. Darius’s paper was first recognized as one of the Top 3% of all papers accepted at the conference, before receiving one of only 5 Best Student Paper Awards during the closing ceremony.
-
- Date: June 9, 2023
Awarded to: Cristian J. Vaca-Rubio, Pu Wang, Toshiaki Koike-Akino, Ye Wang, Petros Boufounos and Petar Popovski
MERL Contacts: Petros T. Boufounos; Toshiaki Koike-Akino; Pu (Perry) Wang; Ye Wang
Research Areas: Artificial Intelligence, Communications, Computational Sensing, Dynamical Systems, Machine Learning, Signal Processing
Brief - A MERL Paper on Wi-Fi sensing was recognized as a Top 3% Paper among all 2709 accepted papers at the 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2023). Co-authored by Cristian Vaca-Rubio and Petar Popovski from Aalborg University, Denmark, and MERL researchers Pu Wang, Toshiaki Koike-Akino, Ye Wang, and Petros Boufounos, the paper "MmWave Wi-Fi Trajectory Estimation with Continous-Time Neural Dynamic Learning" was also a Best Student Paper Award finalist.
Performed during Cristian’s stay at MERL first as a visiting Marie Skłodowska-Curie Fellow and then as a full-time intern in 2022, this work capitalizes on standards-compliant Wi-Fi signals to perform indoor localization and sensing. The paper uses a neural dynamic learning framework to address technical issues such as low sampling rate and irregular sampling intervals.
ICASSP, a flagship conference of the IEEE Signal Processing Society (SPS), was hosted on the Greek island of Rhodes from June 04 to June 10, 2023. ICASSP 2023 marked the largest ICASSP in history, boasting over 4000 participants and 6128 submitted papers, out of which 2709 were accepted.
-
- Date: June 1, 2023
Awarded to: Shih-Lun Wu, Xuankai Chang, Gordon Wichern, Jee-weon Jung, Francois Germain, Jonathan Le Roux, Shinji Watanabe
MERL Contacts: François Germain; Jonathan Le Roux; Gordon Wichern
Research Areas: Artificial Intelligence, Machine Learning, Speech & Audio
Brief - A joint team consisting of members of CMU Professor and MERL Alumn Shinji Watanabe's WavLab and members of MERL's Speech & Audio team ranked 1st out of 11 teams in the DCASE2023 Challenge's Task 6A "Automated Audio Captioning". The team was led by student Shih-Lun Wu and also featured Ph.D. candidate Xuankai Chang, Postdoctoral research associate Jee-weon Jung, Prof. Shinji Watanabe, and MERL researchers Gordon Wichern, Francois Germain, and Jonathan Le Roux.
The IEEE AASP Challenge on Detection and Classification of Acoustic Scenes and Events (DCASE Challenge), started in 2013, has been organized yearly since 2016, and gathers challenges on multiple tasks related to the detection, analysis, and generation of sound events. This year, the DCASE2023 Challenge received over 428 submissions from 123 teams across seven tasks.
The CMU-MERL team competed in the Task 6A track, Automated Audio Captioning, which aims at generating informative descriptions for various sounds from nature and/or human activities. The team's system made strong use of large pretrained models, namely a BEATs transformer as part of the audio encoder stack, an Instructor Transformer encoding ground-truth captions to derive an audio-text contrastive loss on the audio encoder, and ChatGPT to produce caption mix-ups (i.e., grammatical and compact combinations of two captions) which, together with the corresponding audio mixtures, increase not only the amount but also the complexity and diversity of the training data. The team's best submission obtained a SPIDEr-FL score of 0.327 on the hidden test set, largely outperforming the 2nd best team's 0.315.
-
- Date: June 18, 2023 - June 22, 2023
Where: Vancouver/Canada
MERL Contacts: Anoop Cherian; Michael J. Jones; Suhas Lohit; Kuan-Chuan Peng
Research Areas: Artificial Intelligence, Computer Vision, Machine Learning
Brief - MERL researchers are presenting 4 papers and co-organizing a workshop at the CVPR 2023 conference, which will be held in Vancouver, Canada June 18-22. CVPR is one of the most prestigious and competitive international conferences in computer vision. Details are provided below.
1. “Are Deep Neural Networks SMARTer than Second Graders,” by Anoop Cherian, Kuan-Chuan Peng, Suhas Lohit, Kevin Smith, and Joshua B. Tenenbaum
We present SMART: a Simple Multimodal Algorithmic Reasoning Task and the associated SMART-101 dataset for evaluating the abstraction, deduction, and generalization abilities of neural networks in solving visuo-linguistic puzzles designed for children in the 6-8 age group. Our experiments using SMART-101 reveal that powerful deep models are not better than random accuracy when analyzed for generalization. We also evaluate large language models (including ChatGPT) on a subset of SMART-101 and find that while these models show convincing reasoning abilities, their answers are often incorrect.
Paper: https://arxiv.org/abs/2212.09993
2. “EVAL: Explainable Video Anomaly Localization,” by Ashish Singh, Michael J. Jones, and Erik Learned-Miller
This work presents a method for detecting unusual activities in videos by building a high-level model of activities found in nominal videos of a scene. The high-level features used in the model are human understandable and include attributes such as the object class and the directions and speeds of motion. Such high-level features allow our method to not only detect anomalous activity but also to provide explanations for why it is anomalous.
Paper: https://arxiv.org/abs/2212.07900
3. "Aligning Step-by-Step Instructional Diagrams to Video Demonstrations," by Jiahao Zhang, Anoop Cherian, Yanbin Liu, Yizhak Ben-Shabat, Cristian Rodriguez, and Stephen Gould
The rise of do-it-yourself (DIY) videos on the web has made it possible even for an unskilled person (or a skilled robot) to imitate and follow instructions to complete complex real world tasks. In this paper, we consider the novel problem of aligning instruction steps that are depicted as assembly diagrams (commonly seen in Ikea assembly manuals) with video segments from in-the-wild videos. We present a new dataset: Ikea Assembly in the Wild (IAW) and propose a contrastive learning framework for aligning instruction diagrams with video clips.
Paper: https://arxiv.org/pdf/2303.13800.pdf
4. "HaLP: Hallucinating Latent Positives for Skeleton-Based Self-Supervised Learning of Actions," by Anshul Shah, Aniket Roy, Ketul Shah, Shlok Kumar Mishra, David Jacobs, Anoop Cherian, and Rama Chellappa
In this work, we propose a new contrastive learning approach to train models for skeleton-based action recognition without labels. Our key contribution is a simple module, HaLP: Hallucinating Latent Positives for contrastive learning. HaLP explores the latent space of poses in suitable directions to generate new positives. Our experiments using HaLP demonstrates strong empirical improvements.
Paper: https://arxiv.org/abs/2304.00387
The 4th Workshop on Fair, Data-Efficient, and Trusted Computer Vision
MERL researcher Kuan-Chuan Peng is co-organizing the fourth Workshop on Fair, Data-Efficient, and Trusted Computer Vision (https://fadetrcv.github.io/2023/) in conjunction with CVPR 2023 on June 18, 2023. This workshop provides a focused venue for discussing and disseminating research in the areas of fairness, bias, and trust in computer vision, as well as adjacent domains such as computational social science and public policy.
-
- Date: June 8, 2023
Where: Zoom
MERL Contact: Abraham P. Vinod
Research Areas: Artificial Intelligence, Control, Dynamical Systems, Optimization, Robotics
Brief - Abraham Vinod gave an invited talk at the Electrical and Computer Engineering Department, the University of California Santa Cruz, titled "Motion Planning under Constraints and Uncertainty using Data and Reachability". His presentation covered recent work on fast and safe motion planners that can allow for coordination among agents, mitigate uncertainty arising from sensing limitations and simplified models, and tolerate the possibility of failures.
-
- Date: June 30, 2023 - June 2, 2023
Where: San Diego, CA
MERL Contact: Ankush Chakrabarty
Research Areas: Applied Physics, Artificial Intelligence, Control, Data Analytics, Dynamical Systems, Machine Learning, Multi-Physical Modeling, Optimization, Robotics
Brief - Ankush Chakrabarty (researcher, Multiphysical Systems Team) co-organized and spoke at 3 sessions at the 2023 American Control Conference in San Diego, CA. These include: (1) A tutorial session (w/ Stefano Di Cairano) on "Physics Informed Machine Learning for Modeling and Control": an effort with contributions from multiple academic institutes and US research labs; (2) An invited session on "Energy Efficiency in Smart Buildings and Cities" in which his paper (w/ Chris Laughman) on "Local Search Region Constrained Bayesian Optimization for Performance Optimization of Vapor Compression Systems" was nominated for Best Energy Systems Paper Award; and, (3) A special session on Diversity, Equity, and Inclusion to improve recruitment and retention of underrepresented groups in STEM research.
-
- Date: June 2, 2023
Awarded to: Yuki Shirai, Devesh Jha, Arvind Raghunathan and Dennis Hong
MERL Contacts: Devesh K. Jha; Arvind Raghunathan; Yuki Shirai
Research Areas: Artificial Intelligence, Optimization, Robotics
Brief - MERL's paper titled: "Closed-Loop Tactile Controller for Tool Manipulation" Won the Best Poster Award in the workshop on "Embracing contacts : Making robots physically interact with our world". First author and MERL intern, Yuki Shirai, was presented with the award at a ceremony held at ICRA in London. MERL researchers Devesh Jha, Principal Research Scientist, and Arvind Raghunathan, Senior Principal Research Scientist and Senior Team Leader as well as Prof. Dennis Hong of University of California, Los Angeles are also coauthors.
The paper presents a technique to manipulate an object using a tool in a closed-loop fashion using vision-based tactile sensors. More information about the workshop and the various speakers can be found here https://sites.google.com/view/icra2023embracingcontacts/home.
-
- Date: Sunday, June 4, 2023 - Saturday, June 10, 2023
Location: Rhodes Island, Greece
MERL Contacts: Petros T. Boufounos; François Germain; Toshiaki Koike-Akino; Jonathan Le Roux; Dehong Liu; Suhas Lohit; Yanting Ma; Hassan Mansour; Joshua Rapp; Anthony Vetro; Pu (Perry) Wang; Gordon Wichern
Research Areas: Artificial Intelligence, Computational Sensing, Machine Learning, Signal Processing, Speech & Audio
Brief - MERL has made numerous contributions to both the organization and technical program of ICASSP 2023, which is being held in Rhodes Island, Greece from June 4-10, 2023.
Organization
Petros Boufounos is serving as General Co-Chair of the conference this year, where he has been involved in all aspects of conference planning and execution.
Perry Wang is the organizer of a special session on Radar-Assisted Perception (RAP), which will be held on Wednesday, June 7. The session will feature talks on signal processing and deep learning for radar perception, pose estimation, and mutual interference mitigation with speakers from both academia (Carnegie Mellon University, Virginia Tech, University of Illinois Urbana-Champaign) and industry (Mitsubishi Electric, Bosch, Waveye).
Anthony Vetro is the co-organizer of the Workshop on Signal Processing for Autonomous Systems (SPAS), which will be held on Monday, June 5, and feature invited talks from leaders in both academia and industry on timely topics related to autonomous systems.
Sponsorship
MERL is proud to be a Silver Patron of the conference and will participate in the student job fair on Thursday, June 8. Please join this session to learn more about employment opportunities at MERL, including openings for research scientists, post-docs, and interns.
MERL is pleased to be the sponsor of two IEEE Awards that will be presented at the conference. We congratulate Prof. Rabab Ward, the recipient of the 2023 IEEE Fourier Award for Signal Processing, and Prof. Alexander Waibel, the recipient of the 2023 IEEE James L. Flanagan Speech and Audio Processing Award.
Technical Program
MERL is presenting 13 papers in the main conference on a wide range of topics including source separation and speech enhancement, radar imaging, depth estimation, motor fault detection, time series recovery, and point clouds. One workshop paper has also been accepted for presentation on self-supervised music source separation.
Perry Wang has been invited to give a keynote talk on Wi-Fi sensing and related standards activities at the Workshop on Integrated Sensing and Communications (ISAC), which will be held on Sunday, June 4.
Additionally, Anthony Vetro will present a Perspective Talk on Physics-Grounded Machine Learning, which is scheduled for Thursday, June 8.
About ICASSP
ICASSP is the flagship conference of the IEEE Signal Processing Society, and the world's largest and most comprehensive technical conference focused on the research advances and latest technological development in signal and information processing. The event attracts more than 2000 participants each year.
-
- Date & Time: Tuesday, April 25, 2023; 11:00 AM
Speaker: Dan Stowell, Tilburg University / Naturalis Biodiversity Centre
MERL Host: Gordon Wichern
Research Areas: Artificial Intelligence, Machine Learning, Speech & Audio
Abstract 
Machine learning can be used to identify animals from their sound. This could be a valuable tool for biodiversity monitoring, and for understanding animal behaviour and communication. But to get there, we need very high accuracy at fine-grained acoustic distinctions across hundreds of categories in diverse conditions. In our group we are studying how to achieve this at continental scale. I will describe aspects of bioacoustic data that challenge even the latest deep learning workflows, and our work to address this. Methods covered include adaptive feature representations, deep embeddings and few-shot learning.
-
- Date & Time: Tuesday, March 14, 2023; 1:00 PM
Speaker: Suraj Srinivas, Harvard University
MERL Host: Suhas Lohit
Research Areas: Artificial Intelligence, Computer Vision, Machine Learning
Abstract 
In this talk, I will discuss our recent research on understanding post-hoc interpretability. I will begin by introducing a characterization of post-hoc interpretability methods as local function approximators, and the implications of this viewpoint, including a no-free-lunch theorem for explanations. Next, we shall challenge the assumption that post-hoc explanations provide information about a model's discriminative capabilities p(y|x) and instead demonstrate that many common methods instead rely on a conditional generative model p(x|y). This observation underscores the importance of being cautious when using such methods in practice. Finally, I will propose to resolve this via regularization of model structure, specifically by training low curvature neural networks, resulting in improved model robustness and stable gradients.
-
- Date: December 9, 2022
Where: Pittsburg, PA
MERL Contact: Jonathan Le Roux
Research Areas: Artificial Intelligence, Machine Learning, Speech & Audio
Brief - MERL Senior Principal Research Scientist and Speech and Audio Senior Team Leader, Jonathan Le Roux, was invited by Carnegie Mellon University's Language Technology Institute (LTI) to give an invited talk as part of the LTI Colloquium Series. The LTI Colloquium is a prestigious series of talks given by experts from across the country related to different areas of language technologies. Jonathan's talk, entitled "Towards general and flexible audio source separation", presented an overview of techniques developed at MERL towards the goal of robustly and flexibly decomposing and analyzing an acoustic scene, describing in particular the Speech and Audio Team's efforts to extend MERL's early speech separation and enhancement methods to more challenging environments, and to more general and less supervised scenarios.
-
- Date: December 15, 2022 - December 17, 2022
MERL Contacts: Jianlin Guo; Philip V. Orlik; Kieran Parsons
Research Areas: Artificial Intelligence, Data Analytics, Machine Learning
Brief - The performance of manufacturing systems is heavily affected by downtime – the time period that the system halts production due to system failure, anomalous operation, or intrusion. Therefore, it is crucial to detect and diagnose anomalies to allow predictive maintenance or intrusion detection to reduce downtime. This talk, titled "Anomaly detection and diagnosis in manufacturing systems using autoencoder", focuses on tackling the challenges arising from predictive maintenance in manufacturing systems. It presents a structured autoencoder and a pre-processed autoencoder for accurate anomaly detection, as well as a statistical-based algorithm and an autoencoder-based algorithm for anomaly diagnosis.
-
- Date: December 8, 2022
MERL Contacts: Toshiaki Koike-Akino; Pu (Perry) Wang
Research Areas: Artificial Intelligence, Communications, Computational Sensing, Machine Learning, Signal Processing
Brief - On December 8, 2022, MERL researchers Toshiaki Koike-Akino and Pu (Perry) Wang gave a 3.5-hour tutorial presentation at the IEEE Global Communications Conference (GLOBECOM). The talk, titled "Post-Deep Learning Era: Emerging Quantum Machine Learning for Sensing and Communications," addressed recent trends, challenges, and advances in sensing and communications. P. Wang presented on use cases, industry trends, signal processing, and deep learning for Wi-Fi integrated sensing and communications (ISAC), while T. Koike-Akino discussed the future of deep learning, giving a comprehensive overview of artificial intelligence (AI) technologies, natural computing, emerging quantum AI, and their diverse applications. The tutorial was conducted remotely. MERL's quantum AI technology was partly reported in the recent press release (https://us.mitsubishielectric.com/en/news/releases/global/2022/1202-a/index.html).
The IEEE GLOBECOM is a highly anticipated event for researchers and industry professionals in the field of communications. Organized by the IEEE Communications Society, the flagship conference is known for its focus on driving innovation in all aspects of the field. Each year, over 3,000 scientific researchers submit proposals for program sessions at the annual conference. The theme of this year's conference was "Accelerating the Digital Transformation through Smart Communications," and featured a comprehensive technical program with 13 symposia, various tutorials and workshops.
-
- Date: December 2, 2022 - December 8, 2022
MERL Contacts: Matthew Brand; Toshiaki Koike-Akino; Jing Liu; Saviz Mowlavi; Kieran Parsons; Ye Wang
Research Areas: Artificial Intelligence, Control, Dynamical Systems, Machine Learning, Signal Processing
Brief - In addition to 5 papers in recent news (https://www.merl.com/news/news-20221129-1450), MERL researchers presented 2 papers at the NeurIPS Conference Workshop, which was held Dec. 2-8. NeurIPS is one of the most prestigious and competitive international conferences in machine learning.
- “Optimal control of PDEs using physics-informed neural networks” by Saviz Mowlavi and Saleh Nabi
Physics-informed neural networks (PINNs) have recently become a popular method for solving forward and inverse problems governed by partial differential equations (PDEs). By incorporating the residual of the PDE into the loss function of a neural network-based surrogate model for the unknown state, PINNs can seamlessly blend measurement data with physical constraints. Here, we extend this framework to PDE-constrained optimal control problems, for which the governing PDE is fully known and the goal is to find a control variable that minimizes a desired cost objective. We validate the performance of the PINN framework by comparing it to state-of-the-art adjoint-based optimization, which performs gradient descent on the discretized control variable while satisfying the discretized PDE.
- “Learning with noisy labels using low-dimensional model trajectory” by Vasu Singla, Shuchin Aeron, Toshiaki Koike-Akino, Matthew E. Brand, Kieran Parsons, Ye Wang
Noisy annotations in real-world datasets pose a challenge for training deep neural networks (DNNs), detrimentally impacting generalization performance as incorrect labels may be memorized. In this work, we probe the observations that early stopping and low-dimensional subspace learning can help address this issue. First, we show that a prior method is sensitive to the early stopping hyper-parameter. Second, we investigate the effectiveness of PCA, for approximating the optimization trajectory under noisy label information. We propose to estimate the low-rank subspace through robust and structured variants of PCA, namely Robust PCA, and Sparse PCA. We find that the subspace estimated through these variants can be less sensitive to early stopping, and can outperform PCA to achieve better test error when trained on noisy labels.
- In addition, new MERL researcher, Jing Liu, also presented a paper entitled “CoPur: Certifiably Robust Collaborative Inference via Feature Purification" based on his previous work before joining MERL. His paper was elected as a spotlight paper to be highlighted in lightening talks and featured paper panel.
-
- Date: December 2, 2022
MERL Contacts: Toshiaki Koike-Akino; Kieran Parsons; Pu (Perry) Wang; Ye Wang
Research Areas: Artificial Intelligence, Computational Sensing, Machine Learning, Signal Processing, Human-Computer Interaction
Brief - Mitsubishi Electric Corporation announced its development of a quantum artificial intelligence (AI) technology that automatically optimizes inference models to downsize the scale of computation with quantum neural networks. The new quantum AI technology can be integrated with classical machine learning frameworks for diverse solutions.
Mitsubishi Electric has confirmed that the technology can be incorporated in the world's first applications for terahertz (THz) imaging, Wi-Fi indoor monitoring, compressed sensing, and brain-computer interfaces. The technology is based on recent research by MERL's Connectivity & Information Processing team and Computational Sensing team.
Mitsubishi Electric's new quantum machine learning (QML) technology realizes compact inference models by fully exploiting the enormous capacity of quantum computers to express exponentially larger-state space with the number of quantum bits (qubits). In a hybrid combination of both quantum and classical AI, the technology can compensate for limitations of classical AI to achieve superior performance while significantly downsizing the scale of AI models, even when using limited data.
-
- Date & Time: Monday, December 12, 2022; 1:00pm-5:30pm ET
Location: Mitsubishi Electric Research Laboratories (MERL)/Virtual
Research Areas: Applied Physics, Artificial Intelligence, Communications, Computational Sensing, Computer Vision, Control, Data Analytics, Dynamical Systems, Electric Systems, Electronic and Photonic Devices, Machine Learning, Multi-Physical Modeling, Optimization, Robotics, Signal Processing, Speech & Audio, Digital Video
Brief - Join MERL's virtual open house on December 12th, 2022! Featuring a keynote, live sessions, research area booths, and opportunities to interact with our research team. Discover who we are and what we do, and learn about internship and employment opportunities.
-
- Date: November 29, 2022 - December 9, 2022
Where: NeurIPS 2022
MERL Contacts: Moitreya Chatterjee; Anoop Cherian; Michael J. Jones; Suhas Lohit
Research Areas: Artificial Intelligence, Computer Vision, Machine Learning, Speech & Audio
Brief - MERL researchers are presenting 5 papers at the NeurIPS Conference, which will be held in New Orleans from Nov 29-Dec 1st, with virtual presentations in the following week. NeurIPS is one of the most prestigious and competitive international conferences in machine learning.
MERL papers in NeurIPS 2022:
1. “AVLEN: Audio-Visual-Language Embodied Navigation in 3D Environments” by Sudipta Paul, Amit Roy-Chowdhary, and Anoop Cherian
This work proposes a unified multimodal task for audio-visual embodied navigation where the navigating agent can also interact and seek help from a human/oracle in natural language when it is uncertain of its navigation actions. We propose a multimodal deep hierarchical reinforcement learning framework for solving this challenging task that allows the agent to learn when to seek help and how to use the language instructions. AVLEN agents can interact anywhere in the 3D navigation space and demonstrate state-of-the-art performances when the audio-goal is sporadic or when distractor sounds are present.
2. “Learning Partial Equivariances From Data” by David W. Romero and Suhas Lohit
Group equivariance serves as a good prior improving data efficiency and generalization for deep neural networks, especially in settings with data or memory constraints. However, if the symmetry groups are misspecified, equivariance can be overly restrictive and lead to bad performance. This paper shows how to build partial group convolutional neural networks that learn to adapt the equivariance levels at each layer that are suitable for the task at hand directly from data. This improves performance while retaining equivariance properties approximately.
3. “Learning Audio-Visual Dynamics Using Scene Graphs for Audio Source Separation” by Moitreya Chatterjee, Narendra Ahuja, and Anoop Cherian
There often exist strong correlations between the 3D motion dynamics of a sounding source and its sound being heard, especially when the source is moving towards or away from the microphone. In this paper, we propose an audio-visual scene-graph that learns and leverages such correlations for improved visually-guided audio separation from an audio mixture, while also allowing predicting the direction of motion of the sound source.
4. “What Makes a "Good" Data Augmentation in Knowledge Distillation - A Statistical Perspective” by Huan Wang, Suhas Lohit, Michael Jones, and Yun Fu
This paper presents theoretical and practical results for understanding what makes a particular data augmentation technique (DA) suitable for knowledge distillation (KD). We design a simple metric that works very well in practice to predict the effectiveness of DA for KD. Based on this metric, we also propose a new data augmentation technique that outperforms other methods for knowledge distillation in image recognition networks.
5. “FeLMi : Few shot Learning with hard Mixup” by Aniket Roy, Anshul Shah, Ketul Shah, Prithviraj Dhar, Anoop Cherian, and Rama Chellappa
Learning from only a few examples is a fundamental challenge in machine learning. Recent approaches show benefits by learning a feature extractor on the abundant and labeled base examples and transferring these to the fewer novel examples. However, the latter stage is often prone to overfitting due to the small size of few-shot datasets. In this paper, we propose a novel uncertainty-based criteria to synthetically produce “hard” and useful data by mixing up real data samples. Our approach leads to state-of-the-art results on various computer vision few-shot benchmarks.
-
- Date & Time: Tuesday, November 1, 2022; 1:00 PM
Speaker: Jiajun Wu, Stanford University
MERL Host: Anoop Cherian
Research Areas: Artificial Intelligence, Computer Vision, Machine Learning
Abstract 
The visual world has its inherent structure: scenes are made of multiple identical objects; different objects may have the same color or material, with a regular layout; each object can be symmetric and have repetitive parts. How can we infer, represent, and use such structure from raw data, without hampering the expressiveness of neural networks? In this talk, I will demonstrate that such structure, or code, can be learned from natural supervision. Here, natural supervision can be from pixels, where neuro-symbolic methods automatically discover repetitive parts and objects for scene synthesis. It can also be from objects, where humans during fabrication introduce priors that can be leveraged by machines to infer regular intrinsics such as texture and material. When solving these problems, structured representations and neural nets play complementary roles: it is more data-efficient to learn with structured representations, and they generalize better to new scenarios with robustly captured high-level information; neural nets effectively extract complex, low-level features from cluttered and noisy visual data.
-
- Date: October 20, 2022
Where: University Park, PA
MERL Contact: Devesh K. Jha
Research Areas: Artificial Intelligence, Control, Robotics
Brief - Devesh Jha, a Principal Research Scientist in the Data Analytics Group at MERL, delivered an invited talk at The Penn State Seminar Series on Systems, Control and Robotics. This talk presented some of the recent work done at MERL in the areas of optimization and control for robotic manipulation in unstructured environment.
-