Articles with public access mandates - Michael CogswellLearn more
Available somewhere: 6
Grad-cam: Visual explanations from deep networks via gradient-based localization
RR Selvaraju, M Cogswell, A Das, R Vedantam, D Parikh, D Batra
Proceedings of the IEEE international conference on computer vision, 618-626, 2017
Mandates: US National Science Foundation, US Department of Defense
Stochastic multiple choice learning for training diverse deep ensembles
S Lee, S Purushwalkam Shiva Prakash, M Cogswell, V Ranjan, ...
Advances in Neural Information Processing Systems 29, 2016
Mandates: US National Science Foundation
Dialog without dialog data: Learning visual dialog agents from VQA data
M Cogswell, J Lu, R Jain, S Lee, D Parikh, D Batra
Advances in Neural Information Processing Systems 33, 19988-19999, 2020
Mandates: US National Science Foundation, US Department of Defense
Improving users' mental model with attentionâdirected counterfactual edits
K Alipour, A Ray, X Lin, M Cogswell, JP Schulze, Y Yao, GT Burachas
Applied AI Letters 2 (4), e47, 2021
Mandates: US Department of Defense
Knowing what VQA does not: Pointing to error-inducing regions to improve explanation helpfulness
A Ray, M Cogswell, X Lin, K Alipour, A Divakaran, Y Yao, G Burachas
arXiv preprint arXiv 2103, 2021
Mandates: US Department of Defense
Generating and evaluating explanations of attended and errorâinducing input regions for VQA models
A Ray, M Cogswell, X Lin, K Alipour, A Divakaran, Y Yao, G Burachas
Applied AI Letters 2 (4), e51, 2021
Mandates: US Department of Defense
Publication and funding information is determined automatically by a computer program