NEWS    MERL researchers presenting five papers at NeurIPS 2022

Date:

November 29, 2022 - December 9, 2022

Where:

NeurIPS 2022

Description:

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.

External Link:

https://nips.cc/

Research Areas:

Artificial Intelligence, Computer Vision, Machine Learning, Speech & Audio

• Related Publications

   Romero, D., Lohit, S., "Learning Partial Equivariances from Data", Advances in Neural Information Processing Systems (NeurIPS), S. Koyejo and S. Mohamed and A. Agarwal and D. Belgrave and K. Cho and A. Oh, Eds., November 2022, pp. 36466-36478.

  BibTeX TR2022-148 PDF Software Presentation

  • @inproceedings{Romero2022nov,
  • author = {Romero, David and Lohit, Suhas},
  • title = {Learning Partial Equivariances from Data},
  • booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  • year = 2022,
  • editor = {S. Koyejo and S. Mohamed and A. Agarwal and D. Belgrave and K. Cho and A. Oh},
  • pages = {36466--36478},
  • month = nov,
  • url = {https://www.merl.com/publications/TR2022-148}
  • }

   Wang, H., Lohit, S., Jones, M.J., Fu, R., "What Makes a “Good” Data Augmentation in Knowledge Distillation – A Statistical Perspective", Advances in Neural Information Processing Systems (NeurIPS), S. Koyejo and S. Mohamed and A. Agarwal and D. Belgrave and K. Cho and A. Oh, Eds., November 2022, pp. 13456-13469.

  BibTeX TR2022-147 PDF

  • @inproceedings{Wang2022nov,
  • author = {Wang, Huan and Lohit, Suhas and Jones, Michael J. and Fu, Raymond},
  • title = {What Makes a “Good” Data Augmentation in Knowledge Distillation – A Statistical Perspective},
  • booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  • year = 2022,
  • editor = {S. Koyejo and S. Mohamed and A. Agarwal and D. Belgrave and K. Cho and A. Oh},
  • pages = {13456--13469},
  • month = nov,
  • url = {https://www.merl.com/publications/TR2022-147}
  • }

   Chatterjee, M., Ahuja, N., Cherian, A., "Learning Audio-Visual Dynamics Using Scene Graphs for Audio Source Separation", Advances in Neural Information Processing Systems (NeurIPS), November 2022.

  BibTeX TR2022-140 PDF Presentation

  • @inproceedings{Chatterjee2022nov,
  • author = {Chatterjee, Moitreya and Ahuja, Narendra and Cherian, Anoop},
  • title = {Learning Audio-Visual Dynamics Using Scene Graphs for Audio Source Separation},
  • booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  • year = 2022,
  • month = nov,
  • url = {https://www.merl.com/publications/TR2022-140}
  • }

   Paul, S., Roy Chowdhury, A.K., Cherian, A., "AVLEN: Audio-Visual-Language Embodied Navigation in 3D Environments", Advances in Neural Information Processing Systems (NeurIPS), October 2022, pp. 6236-6249.

  BibTeX TR2022-131 PDF Video Data Software

  • @inproceedings{Paul2022oct2,
  • author = {Paul, Sudipta and Roy Chowdhury, Amit K and Cherian, Anoop},
  • title = {AVLEN: Audio-Visual-Language Embodied Navigation in 3D Environments},
  • booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  • year = 2022,
  • pages = {6236--6249},
  • month = oct,
  • url = {https://www.merl.com/publications/TR2022-131}
  • }