CALL FOR PAPERS AND CHALLENGE PARTICIPATION

2nd Causality in Vision (CiV)

http://www.causalityinvision.com

2022 NICO Common Context Generalization Challenge

https://nicochallenge.com

In conjunction with the 17th European Conference on Computer Vision (ECCV 2022)

https://eccv2022.ecva.net

Tel-Aviv, Israel, Oct. 23-27 2022.

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.

CALL FOR PAPERS

We invite submissions of papers related to the applications/theories of causality in computer vision, including but not limited to:

* Causal discovery for high-dimensional visual data

* Causal inference for fair and explainable deep models

* Causal inference for robust visual models

* Causality combined with unsupervised, supervised, and reinforcement learning

* Learning visual causal generative mechanisms

* Structural causal models for heterogeneous and multimodal data

* Novel models combined vision and causality

* Visual causality data collection, benchmarking, and performance evaluation

Workshop submissions are open! Visit the website:

   http://www.causalityinvision.com/submission.html

Important dates:

– Submission deadline: July 22, 2022 (11:59pm Pacific Standard Time).

– Notification to authors: April 17, 2022 (11:59pm Pacific Standard Time).

– Camera-ready deadline: August 22, 2022 (11:59pm Pacific Standard Time).

– Workshop: October 23 or 24, 2022

CALL FOR CHALLENGE PARTICIPATION

The goal of NICO Challenge is to facilitate the OOD (Out-of-Distribution) generalization in visual recognition through promoting the research on the intrinsic learning mechanisms with native invariance and generalization ability. The training data is a mixture of several observed contexts while the test data is composed of unseen contexts. Participants are tasked with developing reliable algorithms across different contexts (domains) to improve the generalization ability of models.

The NICO Challenge is an image recognition competition containing two main tracks: 1) common context generalization (Domain Generalization, DG) track; 2) hybrid context generalization track. The difference of these two tracks is whether the context used in training data for all the categories are aligned (e.g. common contexts) and the availability of context (domain) labels. Same as the classic DG setting, all the contexts are common contexts that are aligned for all categories in both training and test data in the common context generalization track. Nevertheless, both common and unique contexts are used for the hybrid context generalization track where the contexts varies across different categories. Context labels are available for the common context generalization track while unavailable for the hybrid context generalization track.

To participate, please register on host-website [Codalab] and create a team for the challenge.

Track 1: Common Context Generalization

       https://codalab.lisn.upsaclay.fr/competitions/4084

Track 2: Hybrid Context Generalization

       https://codalab.lisn.upsaclay.fr/competitions/4083

Important dates:

– 2022-04-18 Releasing the NICO++ dataset. (See the DATASET)

– 2022-04-20 Start Date of Phase 1.

– 2022-07-10 Deadline of Phase 1. This is the last day for team registration and result submission.

– 2022-07-12 Notification of winner teams in Phase 1. Start Date of Phase 2.

– 2022-07-30 Deadline of Phase 2. This is the last day for Top 10 teams to submit the model.

– 2022-08-10 Notification of Final Winners.

All deadlines are at 23:59 AoE on the corresponding day unless otherwise noted.

Workshop Organizers:

Yulei Niu, Columbia University, New York, United States

Hanwang Zhang, Nanyang Technological University, Singapore

Peng Cui, Tsinghua University, Beijing, China

Song-Chun Zhu, Peking University, Beijing, China

Qianru Sun, Singapore Management University, Singapore

Mike Zheng Shou, National University of Singapore, Singapore

Challenge Organizers:

Peng Cui, Tsinghua University, Beijing, China

Hanwang Zhang, Nanyang Technological University, Singapore

David Lopez-Paz, Meta AI Paris, France