Out-of-distribution detection in long-tailed recognition with calibrated outlier class learning

• Main Authors: MIAO, Wenjun, PANG, Guansong, BAI, Xiao, LI, Tianqi, ZHENG, Jin
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2024
• Subjects: Object Detection & Categorization; Adversarial Attacks & Robustness; Applications; Artificial Intelligence and Robotics; Graphics and Human Computer Interfaces
• Online Access: https://ink.library.smu.edu.sg/sis_research/9872; https://ink.library.smu.edu.sg/context/sis_research/article/10872/viewcontent/28217_Article_Text_32271_1_2_20240324.pdf
• Institution: Singapore Management University

Existing out-of-distribution (OOD) methods have shown great success on balanced datasets but become ineffective in long-tailed recognition (LTR) scenarios where 1) OOD samples are often wrongly classified into head classes and/or 2) tail-class samples are treated as OOD samples. To address these iss...