1st Causality in Vision

CVPR 2021 Workshop, June 19 (EDT 8:00 AM), Virtual



Correlation is not causality. However, this common sense is often surprisingly ignored in most of today’s computer vision systems, including classification, detection, segmentation, and vision-language models, because they are merely trained on correlated sample-label pairs, and the resultant models are nothing short of a likelihood lookup table --- we cannot expect them to generalize to unseen data distribution, not mentioning to more human-level tasks such as modularization, interpretation, and imagination. What is even more regrettable in our community is that we usually blame the poor generalization for insufficient data, and thus some of us may be trapped in the infinite loop: “make a large dataset”---“over-fitted”---“make a larger one’’.

Causality is a new science of data generation, model training, and inference. Only by understanding the data causality, we can remove the spurious bias, disentangle the desired model effects, and modularize reusable features that generalize well. We deeply feel that it is a pressing demand for our CV community to adopt causality and use it as a new mind to re-think the hype of feeding big data into gigantic deep models.

The goal of this workshop is to provide a comprehensive yet accessible overview of existing causality research and to help CV researchers to know why and how to apply causality in their own work. We aim to invite speakers from this area to present their latest works and propose new challenges.

Invited Talks

Bernhard Schölkopf
Songchun Zhu
Susan Athey
(Stanford University)
Max Welling
(University of Amsterdam / Qualcomm)


Time (EDT) Invited speaker Title Recording
8:00 - 8:10 OC Team Opening Remarks YouTube
8:10 - 8:45 Prof. Bernhard Schölkopf Invited Talk 1 TBD
8:45 - 9:20 Prof. Songchun Zhu Invited Talk 2 YouTube
9:20 - 9:30 - Coffee Break
9:30 - 10:05 Prof. Max Welling Invited Talk 3 YouTube
10:05 - 10:40 Prof. Susan Athey Invited Talk 4 YouTube
10:40 - 11:00 Ph.D. Abbavaram Gowtham Reddy Oral Presentation 1 YouTube
11:00 - 11:20 Ph.D. Axel Sauer Oral Presentation 2 YouTube
11:20 - 11:30 OC Team Closing Remarks YouTube

Accepted Papers

Title Authors URL (for poster session) PDF

(Oral) Counterfactual Generative Networks

Axel Sauer, Andreas Geiger YouTube PDF

(Oral) CANDLE: An Image Dataset for Causal Analysis in Disentangled Representations

Abbavaram Gowtham Reddy, Benin Godfrey L, Vineeth N Balasubramanian YouTube PDF [supp]

Shadow-Mapping for Unsupervised Neural Causal Discovery

Matthew Vowels, Necati Cihan Camgoz, Richard Bowden - PDF

DeVLBert: Out-of-distribution Visio-Linguistic Pretraining with Causality

Shengyu Zhang, Tan Jiang, Tan Wang, Kun Kuang, Zhou Zhao, Jianke Zhu, Jin Yu, Hongxia Yang, Fei Wu - PDF

Grounded, Controllable and Debiased Image Completion with Lexical Semantics

Shengyu Zhang, Tan Jiang, Qinghao Huang, Ziqi Tan, Kun Kuang, Zhou Zhao, Siliang Tang, Jin Yu, Hongxia Yang, Yi Yang, Fei Wu - PDF

Learning Contextual Causality between Daily Events from Time-consecutive Images

Hongming Zhang, Yintong Huo, Xinran Zhao, Yangqiu Song, Dan Roth - PDF

Instance-wise Causal Feature Selection for Model Interpretation

Pranoy Panda, Sai Srinivas Kancheti, Vineeth N Balasubramanian - PDF

Matched sample selection with GANs for mitigating attribute confounding

Chandan Singh, Guha Balakrishnan, Pietro Perona - PDF

A causal view of compositional zero-shot recognition

Yuval Atzmon, Felix Kreuk, Uri Shalit, Gal Chechik - PDF

Path Intervention for Path-specific Effects

Heyang Gong - PDF


Hanwang Zhang (Nanyang Technological University) Peng Cui (Tsinghua University) Kun Zhang (Carnegie Mellon University) Qianru Sun (Singapore Management University)
Mario Fritz (CISPA Helmholtz Center for Information Security) Kaihua Tang (Nanyang Technological University) Yulei Niu (Nanyang Technological University)

Workshop Sponsor

Best Paper Sponsor