Lune

CVPR Findings2026

Long-Tailed Out-of-Distribution Detection with Refined Separate Class Learning

Shuai Feng, Yuxin Ge, Baoming Zhang, Yuntao Du, MingCai Chen, Chongjun Wang, Lei Feng

Abstract

Out-of-distribution (OOD) detection is crucial for deploying robust machine learning models. However, when training data follows a long-tailed distribution, the model's ability to accurately detect OOD samples is significantly compromised, due to the confusion between OOD samples and head/tail classes. To distinguish OOD samples from both head and tail classes, the separate class learning (SCL) approach has emerged as a promising solution, which conducts head-specific and tail-specific class learning separately. Building upon this, we examine the limitations of existing works of SCL and reveal that the OOD detection performance is sensitive to static temperature value and subject to the impact of informative outliers. To mitigate these limitations, we propose a novel approach termed Refined Separate Class Learning (RSCL), which leverages dynamic class-wise temperature adjustment to modulate the temperature parameter for each in-distribution class and utilizes informative outlier mining to identify diverse types of outliers based on their affinity with head and tail classes. Extensive experiments demonstrate that RSCL achieves superior OOD detection performance while improving classification accuracy on in-distribution data. Code is available at https://github.com/RSCL.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Long-tail learning via logit adjustment cites Decoupling Representation and Classifier for Long-Tailed Recognition
  • Out-of-Distribution Detection with Deep Nearest Neighbors cites Energy-based Out-of-distribution Detection
  • Out-of-Distribution Detection with Deep Nearest Neighbors cites Supervised Contrastive Learning
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on24

  1. Supervised Contrastive LearningPrannay Khosla, Piotr Teterwak, Chen Wang, Aaron Sarna et al.NeurIPS 2020 · 7,049 citations
  2. Energy-based Out-of-distribution DetectionWeitang Liu, Xiaoyun Wang, John D. Owens, Yixuan LiNeurIPS 2020 · 2,213 citations
  3. Decoupling Representation and Classifier for Long-Tailed RecognitionBingyi Kang, Saining Xie, Marcus Rohrbach, Zhicheng Yan et al.ICLR 2020 · 1,496 citations
  4. Long-tail learning via logit adjustmentAditya Krishna Menon, Sadeep Jayasumana, Ankit Singh Rawat, Himanshu Jain et al.ICLR 2021 · 937 citations
  5. Out-of-Distribution Detection with Deep Nearest NeighborsYiyou Sun, Yifei Ming, Xiaojin Zhu, Yixuan LiICML 2022 · 789 citations

Related papers

  1. Out-of-Distribution Detection in Long-Tailed Recognition with Calibrated Outlier Class LearningWenjun Miao, Guansong Pang, Xiao Bai, Tianqi Li et al.AAAI 2024 · 31 citations
  2. EAT: Towards Long-Tailed Out-of-Distribution DetectionTong Wei, Bo-Lin Wang, Min-Ling ZhangAAAI 2024 · 21 citations
  3. Partial and Asymmetric Contrastive Learning for Out-of-Distribution Detection in Long-Tailed RecognitionHaotao Wang, Aston Zhang, Yi Zhu, Shuai Zheng et al.ICML 2022 · 61 citations
  4. Long-Tailed Out-of-Distribution Detection: Prioritizing Attention to TailYina He, Lei Peng, Yongcun Zhang, Juanjuan Weng et al.AAAI 2025 · 5 citations
  5. Exploiting Mixed Unlabeled Data for Detecting Samples of Seen and Unseen Out-of-Distribution ClassesYi-Xuan Sun, Wei WangAAAI 2022 · 5 citations
Dusk over the sea between two cliffs drawn in fine vertical lines