Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Dilip Krishnan

Unsupervised Disentanglement without Autoencoding: Pitfalls and Future Directions


Aug 14, 2021
Andrea Burns, Aaron Sarna, Dilip Krishnan, Aaron Maschinot

* Accepted at the ICML 2021 Self-Supervised Learning for Reasoning and Perception Workshop 

  Access Paper or Ask Questions

Understanding invariance via feedforward inversion of discriminatively trained classifiers


Mar 15, 2021
Piotr Teterwak, Chiyuan Zhang, Dilip Krishnan, Michael C. Mozer


  Access Paper or Ask Questions

What makes for good views for contrastive learning


May 20, 2020
Yonglong Tian, Chen Sun, Ben Poole, Dilip Krishnan, Cordelia Schmid, Phillip Isola

* submitted to ECCV 2020 

  Access Paper or Ask Questions

Supervised Contrastive Learning


Apr 23, 2020
Prannay Khosla, Piotr Teterwak, Chen Wang, Aaron Sarna, Yonglong Tian, Phillip Isola, Aaron Maschinot, Ce Liu, Dilip Krishnan


  Access Paper or Ask Questions

Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?


Mar 25, 2020
Yonglong Tian, Yue Wang, Dilip Krishnan, Joshua B. Tenenbaum, Phillip Isola

* First two authors contributed equally. Code: http://github.com/WangYueFt/rfs/ 

  Access Paper or Ask Questions

Fantastic Generalization Measures and Where to Find Them


Dec 04, 2019
Yiding Jiang, Behnam Neyshabur, Hossein Mobahi, Dilip Krishnan, Samy Bengio


  Access Paper or Ask Questions

Contrastive Representation Distillation


Oct 23, 2019
Yonglong Tian, Dilip Krishnan, Phillip Isola

* Project Page: http://hobbitlong.github.io/CRD/, Code: http://github.com/HobbitLong/RepDistiller 

  Access Paper or Ask Questions

Boundless: Generative Adversarial Networks for Image Extension


Aug 19, 2019
Piotr Teterwak, Aaron Sarna, Dilip Krishnan, Aaron Maschinot, David Belanger, Ce Liu, William T. Freeman


  Access Paper or Ask Questions

Adversarial Robustness through Local Linearization


Jul 04, 2019
Chongli Qin, James Martens, Sven Gowal, Dilip Krishnan, Krishnamurthy, Dvijotham, Alhussein Fawzi, Soham De, Robert Stanforth, Pushmeet Kohli


  Access Paper or Ask Questions

Contrastive Multiview Coding


Jun 23, 2019
Yonglong Tian, Dilip Krishnan, Phillip Isola

* In submission. Code: http://github.com/HobbitLong/CMC/ 

  Access Paper or Ask Questions

A Closed-Form Learned Pooling for Deep Classification Networks


Jun 10, 2019
Vighnesh Birodkar, Hossein Mobahi, Dilip Krishnan, Samy Bengio


  Access Paper or Ask Questions

Predicting the Generalization Gap in Deep Networks with Margin Distributions


Sep 28, 2018
Yiding Jiang, Dilip Krishnan, Hossein Mobahi, Samy Bengio


  Access Paper or Ask Questions

Smart, Sparse Contours to Represent and Edit Images


Apr 09, 2018
Tali Dekel, Chuang Gan, Dilip Krishnan, Ce Liu, William T. Freeman

* Accepted to CVPR'18; Project page: contour2im.github.io 

  Access Paper or Ask Questions

Large Margin Deep Networks for Classification


Mar 15, 2018
Gamaleldin F. Elsayed, Dilip Krishnan, Hossein Mobahi, Kevin Regan, Samy Bengio


  Access Paper or Ask Questions

Synthesizing Normalized Faces from Facial Identity Features


Oct 17, 2017
Forrester Cole, David Belanger, Dilip Krishnan, Aaron Sarna, Inbar Mosseri, William T. Freeman


  Access Paper or Ask Questions

Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks


Aug 23, 2017
Konstantinos Bousmalis, Nathan Silberman, David Dohan, Dumitru Erhan, Dilip Krishnan

* Final CVPR 2017 paper and supplementary material 

  Access Paper or Ask Questions

Domain Separation Networks


Aug 22, 2016
Konstantinos Bousmalis, George Trigeorgis, Nathan Silberman, Dilip Krishnan, Dumitru Erhan

* This work will be presented at NIPS 2016 

  Access Paper or Ask Questions

Learning visual groups from co-occurrences in space and time


Nov 21, 2015
Phillip Isola, Daniel Zoran, Dilip Krishnan, Edward H. Adelson


  Access Paper or Ask Questions

Blind Deconvolution with Non-local Sparsity Reweighting


Jun 16, 2014
Dilip Krishnan, Joan Bruna, Rob Fergus

* 19 pages 

  Access Paper or Ask Questions