Interpret Your Decision: Logical Reasoning Regularization for Generalization in Visual Classification

Autor:	Tan, Zhaorui, Yang, Xi, Wang, Qiufeng, Nguyen, Anh, Huang, Kaizhu
Rok vydání:	2024
Předmět:	Computer Science - Computer Vision and Pattern Recognition Computer Science - Artificial Intelligence Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	Vision models excel in image classification but struggle to generalize to unseen data, such as classifying images from unseen domains or discovering novel categories. In this paper, we explore the relationship between logical reasoning and deep learning generalization in visual classification. A logical regularization termed L-Reg is derived which bridges a logical analysis framework to image classification. Our work reveals that L-Reg reduces the complexity of the model in terms of the feature distribution and classifier weights. Specifically, we unveil the interpretability brought by L-Reg, as it enables the model to extract the salient features, such as faces to persons, for classification. Theoretical analysis and experiments demonstrate that L-Reg enhances generalization across various scenarios, including multi-domain generalization and generalized category discovery. In complex real-world scenarios where images span unknown classes and unseen domains, L-Reg consistently improves generalization, highlighting its practical efficacy. Comment: Accepted by NeurIPS2024 as Spotlight
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2410.04492 Zobrazit plný text záznamu View this record from Arxiv