Hi! I’m a PhD student working with Dhruv Batra. I try to understand Neural Networks, especially as applied to Computer Vision. As deep networks become more widely used, I hope to find new ways for users to understand the complex systems they use and to leverage this understanding to build better models.

Publications

Grad-CAM: Why did you say that? Visual Explanations from Deep Networks via Gradient-based Localization
Ramprasaath R. Selvaraju, Abhishek Das, Ramakrishna Vedantam, Michael Cogswell, Devi Parikh, Dhruv Batra
(NIPS 2016 Workshop – Interpretable ML for Complex Systems)
[arXiv] [code] [demo]

Stochastic Multiple Choice Learning for Training Diverse Deep Ensembles
Stefan Lee, Senthil Purushwalkam, Michael Cogswell, Viresh Ranjan, David Crandall, Dhruv Batra
(NIPS 2016)
[arXiv]

Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models
Ashwin K Vijayakumar, Michael Cogswell, Ramprasath R. Selvaraju, Qing Sun, Stefan Lee, David Crandall, Dhruv Batra
(arXiv preprint)
[arXiv] [demo]

Reducing Overfitting in Deep Networks by Decorrelating Representations
Michael Cogswell, Faruk Ahmed, Ross Girshick, Larry Zitnick, Dhruv Batra
(ICLR 2016)
[arXiv]

Why M heads are better than one: Training a diverse ensemble of deep networks (similar to Lee et. al. 2016)
Stefan Lee, Senthil Purushwalkam, Michael Cogswell, David Crandall, Dhruv Batra
(arXiv preprint)
[arXiv]

Combining the best of graphical models and convnets for semantic segmentation
Michael Cogswell, Xiao Lin, Senthil Purushwalkam, Dhruv Batra
(arXiv preprint)
[arXiv]