Estimating Noisy Class Posterior with Part-level Labels for Noisy Label Learning
Authors:
- 16 June 2024
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 22809-22819
Abstract
In noisy label learning, estimating noisy class posteriors plays a fundamental role for developing consistent classifiers, as it forms the basis for estimating clean class posteriors and the transition matrix. Existing methods typically learn noisy class posteriors by training a classification model with noisy labels. However, when labels are incorrect, these models may be misled to overemphasize the feature parts that do not reflect the instance characteristics, resulting in significant errors in estimating noisy class posteriors. To address this issue, this paper proposes to augment the supervised information with part-level labels, encouraging the model to focus on and integrate richer information from various parts. Specifically, our method first partitions features into distinct parts by cropping instances, yielding part-level labels associated with these various parts. Subsequently, we introduce a novel single-to-multiple transition matrix to model the relationship between the noisy and part-level labels, which incorporates part-level labels into a classifier-consistent framework. Utilizing this framework with part-level labels, we can learn the noisy class posteriors more precisely by guiding the model to integrate information from various parts, ultimately improving the classification performance. Our method is theoretically sound, while experiments show that it is empirically effective in synthetic and real-world noisy benchmarks.Keywords
All Related Versions
This publication has 24 references indexed in Scilit:
- Neighborhood Collective Estimation for Noisy Label Identification and Correction2022
- BoundaryFace: A Mining Framework with Noise Label Self-correction for Face Recognition2022
- Making Deep Neural Networks Robust to Label Noise: A Loss Correction Approach2017
- Identity Mappings in Deep Residual Networks2016
- Learning from massive noisy labeled data for image classification2015
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- Solving the multiple instance problem with axis-parallel rectanglesArtificial Intelligence, 1997
- Recognition of Objects and Their Component Parts: Responses of Single Units in the Temporal Cortex of the MacaqueCerebral Cortex, 1994
- Recognition-by-components: A theory of human image understanding.Psychological Review, 1987
- Hierarchical structure in perceptual representationCognitive Psychology, 1977