Counterfactual Reasoning for Multi-Label Image Classification via Patching-Based Training

arXiv:2404.06287v1 Announce Type: cross
Abstract: The key to multi-label image classification (MLC) is to improve model performance by leveraging label correlations. Unfortunately, it has been shown that overemphasizing co-occurrence relationships can cause the overfitting issue of the model, ultimately leading to performance degradation. In this paper, we provide a causal inference framework to show that the correlative features caused by the target object and its co-occurring objects can be regarded as a mediator, which has both positive and negative impacts …

abstract arxiv causal causal inference classification correlations counterfactual cs.cv cs.lg image inference issue key mlc overfitting paper performance reasoning relationships the key training type via