Label-Noise Learning with Intrinsically Long-Tailed Data

Yang Lu*, Yiliang Zhang, Bo Han, Yiu Ming Cheung, Hanzi Wang

*Corresponding author for this work

Research output: Chapter in book/report/conference proceedingConference proceedingpeer-review

2 Citations (Scopus)


Label noise is one of the key factors that lead to the poor generalization of deep learning models. Existing label-noise learning methods usually assume that the ground-truth classes of the training data are balanced. However, the real-world data is often imbalanced, leading to the inconsistency between observed and intrinsic class distribution with label noises. In this case, it is hard to distinguish clean samples from noisy samples on the intrinsic tail classes with the unknown intrinsic class distribution. In this paper, we propose a learning frame-work for label-noise learning with intrinsically long-tailed data. Specifically, we propose two-stage bi-dimensional sample selection (TABASCO) to better separate clean samples from noisy samples, especially for the tail classes. TABASCO consists of two new separation metrics that complement each other to compensate for the limitation of using a single metric in sample separation. Extensive experiments on benchmarks demonstrate the effectiveness of our method. Our code is available at

Original languageEnglish
Title of host publicationProceedings - 2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023
Number of pages10
ISBN (Electronic)9798350307184
ISBN (Print)9798350307191
Publication statusPublished - 2 Oct 2023
Event2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023 - Paris, France
Duration: 2 Oct 20236 Oct 2023 (Conference website) (Conference proceedings)

Publication series

NameProceedings of the IEEE International Conference on Computer Vision
ISSN (Print)1550-5499
ISSN (Electronic)2380-7504


Conference2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023
Internet address

Scopus Subject Areas

  • Software
  • Computer Vision and Pattern Recognition


Dive into the research topics of 'Label-Noise Learning with Intrinsically Long-Tailed Data'. Together they form a unique fingerprint.

Cite this