Visual Out-of-Distribution Detection in Open-Set Noisy Environments

• Published in: International journal of computer vision 2024-11, Vol.132 (11), p.5453-5470
• Main Authors: He, Rundong, Han, Zhongyi, Nie, Xiushan, Yin, Yilong, Chang, Xiaojun
• Format: Article
• Language: English
• Subjects: Artificial Intelligence; Computer Imaging; Computer Science; Confounding (Statistics); Image Processing and Computer Vision; Invariants; Machine learning; Optimization; Pattern Recognition; Pattern Recognition and Graphics; Representations; Special Issue on Open-World Visual Recognition; Vision
• ISSN: 0920-5691; 1573-1405
• DOI: 10.1007/s11263-024-02139-y

The presence of noisy examples in the training set inevitably hampers the performance of out-of-distribution (OOD) detection. In this paper, we investigate a previously overlooked problem called OOD detection under asymmetric open-set noise, which is frequently encountered and significantly reduces the identifiability of OOD examples. We analyze the generating process of asymmetric open-set noise and observe the influential role of the confounding variable, entangling many open-set noisy examples with partial in-distribution (ID) examples referred to as hard-ID examples due to spurious-related characteristics. To address the issue of the confounding variable, we propose a novel method called Adversarial Confounder REmoving (ACRE) that utilizes progressive optimization with adversarial learning to curate three collections of potential examples (easy-ID, hard-ID, and open-set noisy) while simultaneously developing invariant representations and reducing spurious-related representations. Specifically, by obtaining easy-ID examples with minimal confounding effect, we learn invariant representations from ID examples that aid in identifying hard-ID and open-set noisy examples based on their similarity to the easy-ID set. By triplet adversarial learning, we achieve the joint minimization and maximization of distribution discrepancies across the three collections, enabling the dual elimination of the confounding variable. We also leverage potential open-set noisy examples to optimize a K +1-class classifier, further removing the confounding variable and inducing a tailored K +1-Guided scoring function. Theoretical analysis establishes the feasibility of ACRE, and extensive experiments demonstrate its effectiveness and generalization. Code is available at https://github.com/Anonymous-re-ssl/ACRE0 .