Michael Cogswell
Michael Cogswell
Vahvistettu sähköpostiosoite verkkotunnuksessa sri.com - Kotisivu
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
Reducing overfitting in deep networks by decorrelating representations
M Cogswell, F Ahmed, R Girshick, L Zitnick, D Batra
arXiv preprint arXiv:1511.06068, 2015
Diverse beam search: Decoding diverse solutions from neural sequence models
AK Vijayakumar, M Cogswell, RR Selvaraju, Q Sun, S Lee, D Crandall, ...
arXiv preprint arXiv:1610.02424, 2016
Why M heads are better than one: Training a diverse ensemble of deep networks
S Lee, S Purushwalkam, M Cogswell, D Crandall, D Batra
arXiv preprint arXiv:1511.06314, 2015
Stochastic multiple choice learning for training diverse deep ensembles
S Lee, SPS Prakash, M Cogswell, V Ranjan, D Crandall, D Batra
Advances in Neural Information Processing Systems, 2119-2127, 2016
Diverse beam search for improved description of complex scenes
AK Vijayakumar, M Cogswell, RR Selvaraju, Q Sun, S Lee, D Crandall, ...
Thirty-Second AAAI Conference on Artificial Intelligence, 2018
Running students' software tests against each others' code: new life for an old" gimmick"
SH Edwards, Z Shams, M Cogswell, RC Senkbeil
Proceedings of the 43rd ACM technical symposium on Computer Science …, 2012
Emergence of compositional language with deep generational transmission
M Cogswell, J Lu, S Lee, D Parikh, D Batra
arXiv preprint arXiv:1904.09067, 2019
Combining the best of graphical models and convnets for semantic segmentation
M Cogswell, X Lin, S Purushwalkam, D Batra
arXiv preprint arXiv:1412.4313, 2014
Dialog without dialog data: Learning visual dialog agents from vqa data
M Cogswell, J Lu, R Jain, S Lee, D Parikh, D Batra
arXiv preprint arXiv:2007.12750, 2020
Abhishek Das
A Das, S Kottur, JMF Moura, S Lee, D Batra, V Dialog, K Gupta, A Singh, ...
Understanding Representations and Reducing their Redundancy in Deep Networks
MA Cogswell
Virginia Tech, 2016
Semantic segmentation with deep learning
M Cogswell, D Batra
Scene Understanding Workshop (SUNw) on CVPR, 2014
Trigger Hunting with a Topological Prior for Trojan Detection
X Hu, X Lin, M Cogswell, Y Yao, S Jha, C Chen
arXiv preprint arXiv:2110.08335, 2021
Improving Users' Mental Model with Attention-directed Counterfactual Edits
K Alipour, A Ray, X Lin, M Cogswell, JP Schulze, Y Yao, GT Burachas
arXiv preprint arXiv:2110.06863, 2021
Generating and Evaluating Explanations of Attended and Error-Inducing Input Regions for VQA Models
A Ray, M Cogswell, X Lin, K Alipour, A Divakaran, Y Yao, G Burachas
Authorea Preprints, 2021
Comprehension Based Question Answering using Bloom's Taxonomy
P Sahu, M Cogswell, S Rutherford-Quach, A Divakaran
arXiv preprint arXiv:2106.04653, 2021
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:2103.14712, 2021
Disentangling neural network representations for improved generalization
MA Cogswell
Georgia Institute of Technology, 2020
Reducing Overfitting in Deep Networks by Decorrelating Representations Download PDF
M Cogswell, F Ahmed, R Girshick, L Zitnick, D Batra
Järjestelmä ei voi suorittaa toimenpidettä nyt. Yritä myöhemmin uudelleen.
Artikkelit 1–20