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 David Bau

Paint by Word


Mar 24, 2021
David Bau, Alex Andonian, Audrey Cui, YeonHwan Park, Ali Jahanian, Aude Oliva, Antonio Torralba

* 10 pages, 9 figures 

  Access Paper or Ask Questions

Understanding the Role of Individual Units in a Deep Neural Network


Sep 12, 2020
David Bau, Jun-Yan Zhu, Hendrik Strobelt, Agata Lapedriza, Bolei Zhou, Antonio Torralba

* Proceedings of the National Academy of Sciences 2020. Code at https://github.com/davidbau/dissect/ and website at https://dissect.csail.mit.edu/ 

  Access Paper or Ask Questions

What makes fake images detectable? Understanding properties that generalize


Aug 24, 2020
Lucy Chai, David Bau, Ser-Nam Lim, Phillip Isola


  Access Paper or Ask Questions

Rewriting a Deep Generative Model


Jul 30, 2020
David Bau, Steven Liu, Tongzhou Wang, Jun-Yan Zhu, Antonio Torralba

* ECCV 2020 (oral). Code at https://github.com/davidbau/rewriting. For videos and demos see https://rewriting.csail.mit.edu/ 

  Access Paper or Ask Questions

Diverse Image Generation via Self-Conditioned GANs


Jun 18, 2020
Steven Liu, Tongzhou Wang, David Bau, Jun-Yan Zhu, Antonio Torralba

* CVPR 2020. Code: https://github.com/stevliu/self-conditioned-gan. Webpage: http://selfcondgan.csail.mit.edu/ 

  Access Paper or Ask Questions

Semantic Photo Manipulation with a Generative Image Prior


May 15, 2020
David Bau, Hendrik Strobelt, William Peebles, Jonas, Bolei Zhou, Jun-Yan Zhu, Antonio Torralba

* Bau, David, et al. "Semantic photo manipulation with a generative image prior." ACM Transactions on Graphics (TOG) 38.4 (2019) 
* SIGGRAPH 2019 

  Access Paper or Ask Questions

Seeing What a GAN Cannot Generate


Oct 24, 2019
David Bau, Jun-Yan Zhu, Jonas Wulff, William Peebles, Hendrik Strobelt, Bolei Zhou, Antonio Torralba

* ICCV 2019 oral; http://ganseeing.csail.mit.edu/ 

  Access Paper or Ask Questions

Dissecting Pruned Neural Networks


Jun 29, 2019
Jonathan Frankle, David Bau


  Access Paper or Ask Questions

Visualizing and Understanding Generative Adversarial Networks (Extended Abstract)


Jan 29, 2019
David Bau, Jun-Yan Zhu, Hendrik Strobelt, Bolei Zhou, Joshua B. Tenenbaum, William T. Freeman, Antonio Torralba

* In AAAI-19 workshop on Network Interpretability for Deep Learning arXiv admin note: substantial text overlap with arXiv:1811.10597 

  Access Paper or Ask Questions

GAN Dissection: Visualizing and Understanding Generative Adversarial Networks


Dec 08, 2018
David Bau, Jun-Yan Zhu, Hendrik Strobelt, Bolei Zhou, Joshua B. Tenenbaum, William T. Freeman, Antonio Torralba

* 18 pages, 19 figures 

  Access Paper or Ask Questions

Interpreting Deep Visual Representations via Network Dissection


Jun 26, 2018
Bolei Zhou, David Bau, Aude Oliva, Antonio Torralba

* *B. Zhou and D. Bau contributed equally to this work. 15 pages, 27 figures 

  Access Paper or Ask Questions

Revisiting the Importance of Individual Units in CNNs via Ablation


Jun 07, 2018
Bolei Zhou, Yiyou Sun, David Bau, Antonio Torralba


  Access Paper or Ask Questions

Explaining Explanations: An Approach to Evaluating Interpretability of Machine Learning


Jun 04, 2018
Leilani H. Gilpin, David Bau, Ben Z. Yuan, Ayesha Bajwa, Michael Specter, Lalana Kagal

* Edited author email 

  Access Paper or Ask Questions

Network Dissection: Quantifying Interpretability of Deep Visual Representations


Apr 19, 2017
David Bau, Bolei Zhou, Aditya Khosla, Aude Oliva, Antonio Torralba

* First two authors contributed equally. Oral presentation at CVPR 2017 

  Access Paper or Ask Questions