paperlist.ai

CVPR 2023 Papers

Conference on Computer Vision and Pattern Recognition

202620252024202320222021202020192018201720162015

Decision breakdown

2,359papers

Counted from the official paper list; may differ slightly from the number the conference announced.

  • Poster
    2,13690.5%
  • Other / unlabeled
    2239.5%

Top 10 topics (click to filter)

Trends for all 207 research topics

Browse all papers

All2,359Poster2,136
Meta-Causal Learning for Single Domain Generalization

Jin Chen, Zhi Gao, Xinxiao Wu, Jiebo Luo

Expand abstract

Single domain generalization aims to learn a model from a single training domain (source domain) and apply it to multiple unseen test domains (target domains). Existing methods focus on expanding the distribution of the training domain to cover the target domains, but without estimating the domain shift between the source and target domains. In this paper, we propose a new learning paradigm, namely simulate-analyze-reduce, which first simulates the domain shift by building an auxiliary domain as the target domain, then learns to analyze the causes of domain shift, and finally learns to reduce the domain shift for model adaptation. Under this paradigm, we propose a meta-causal learning method to learn meta-knowledge, that is, how to infer the causes of domain shift between the auxiliary and source domains during training. We use the meta-knowledge to analyze the shift between the target and source domains during testing. Specifically, we perform multiple transformations on source data to generate the auxiliary domain, perform counterfactual inference to learn to discover the causal factors of the shift between the auxiliary and source domains, and incorporate the inferred causality into factor-aware domain alignments. Extensive experiments on several benchmarks of image classification show the effectiveness of our method.

Poster
Deep learning · causal inferenceCausal Recommendation
CafeBoost: Causal Feature Boost To Eliminate Task-Induced Bias for Class Incremental Learning

Benliu Qiu, Hongliang Li, Haitao Wen, Heqian Qiu, Lanxiao Wang, Fanman Meng, Qingbo Wu, Lili Pan

Expand abstract

Continual learning requires a model to incrementally learn a sequence of tasks and aims to predict well on all the learned tasks so far, which notoriously suffers from the catastrophic forgetting problem. In this paper, we find a new type of bias appearing in continual learning, coined as task-induced bias. We place continual learning into a causal framework, based on which we find the task-induced bias is reduced naturally by two underlying mechanisms in task and domain incremental learning. However, these mechanisms do not exist in class incremental learning (CIL), in which each task contains a unique subset of classes. To eliminate the task-induced bias in CIL, we devise a causal intervention operation so as to cut off the causal path that causes the task-induced bias, and then implement it as a causal debias module that transforms biased features into unbiased ones. In addition, we propose a training pipeline to incorporate the novel module into existing methods and jointly optimize the entire architecture. Our overall approach does not rely on data replay, and is simple and convenient to plug into existing methods. Extensive empirical study on CIFAR-100 and ImageNet shows that our approach can improve accuracy and reduce forgetting of well-established methods by a large margin.

Poster
Deep learning · causal inferenceCausal Recommendation