Extracting Clean and Balanced Subset for Noisy Long-tailed Classification
원문 초록
Real-world datasets usually are class-imbalanced and corrupted by label noise. To solve the joint issue of long-tailed distribution and label noise, most previous works usually aim to design a noise detector to distinguish the noisy and clean samples. Despite their effectiveness, they may be limited in handling the joint issue effectively in a unified way. In this work, we develop a novel pseudo labeling method using class prototypes from the perspective of distribution matching, which can be solved with optimal transport (OT). By setting a manually-specific probability measure and using a learned transport plan to pseudo-label the training samples, the proposed method can reduce the side-effects of noisy and long-tailed data simultaneously. Then we introduce a simple yet effective filter criteria by combining the observed labels and pseudo labels to obtain a more balanced and less noisy subset for a robust model training. Extensive experiments demonstrate that our method can extract this class-balanced subset with clean labels, which brings effective performance gains for long-tailed classification with label noise.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Semi-Supervised Biomedical Image Segmentation via Diffusion Models and Teacher-Student Co-Training
QUEST: Quality-aware Semi-supervised Table Extraction for Business Documents
SRPL-SFDA: SAM-Guided Reliable Pseudo-Labels for Source-Free Domain Adaptation in Medical Image Segmentation
Shuffle PatchMix Augmentation with Confidence-Margin Weighted Pseudo-Labels for Enhanced Source-Free Domain Adaptation
RefAV: Towards Planning-Centric Scenario Mining
A Square Peg in a Square Hole: Meta-Expert for Long-Tailed Semi-Supervised Learning
토론
이 논문과 연결된 포럼 글이 아직 없습니다.