Learning from Imperfect Text Guidance: Robust Long-Tail Visual Recognition with High-Noise Label

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Mengke, Ling, Haiquan, Zhang, Yiqun, Lu, Yang, Huang, Hui
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911622589579264
author Li, Mengke
Ling, Haiquan
Zhang, Yiqun
Lu, Yang
Huang, Hui
author_facet Li, Mengke
Ling, Haiquan
Zhang, Yiqun
Lu, Yang
Huang, Hui
contents Real-world data often exhibit long-tailed distributions with numerous noisy labels, substantially degrading the performance of deep models. While prior research has made progress in addressing this combined challenge, it overlooks the severe label-image mismatch inherent to high-noise settings, thereby limiting their effectiveness. Given that observed labels, though mismatched with images, still retain category information, we propose employing auxiliary text information from labels to address label-image inconsistencies in long-tailed noisy data. Specifically, we leverage the intrinsic cross-modal alignment in pre-trained visual-language models to correct the label-image inconsistencies. This supervisory signal, referred to as Weak Teacher Supervision (WTS), is unaffected by label noise and data distribution biases, albeit exhibits limited accuracy. Therefore, the activation of WTS is determined by evaluating the discrepancy between text-predicted labels and observed labels. Extensive experiments demonstrate the superior performance of WTS across synthetic and real-world datasets, particularly under high-noise conditions. The source code is available at https://anonymous.4open.science/r/WTS-0F3C.
format Preprint
id arxiv_https___arxiv_org_abs_2604_23125
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Learning from Imperfect Text Guidance: Robust Long-Tail Visual Recognition with High-Noise Label
Li, Mengke
Ling, Haiquan
Zhang, Yiqun
Lu, Yang
Huang, Hui
Computer Vision and Pattern Recognition
Machine Learning
Real-world data often exhibit long-tailed distributions with numerous noisy labels, substantially degrading the performance of deep models. While prior research has made progress in addressing this combined challenge, it overlooks the severe label-image mismatch inherent to high-noise settings, thereby limiting their effectiveness. Given that observed labels, though mismatched with images, still retain category information, we propose employing auxiliary text information from labels to address label-image inconsistencies in long-tailed noisy data. Specifically, we leverage the intrinsic cross-modal alignment in pre-trained visual-language models to correct the label-image inconsistencies. This supervisory signal, referred to as Weak Teacher Supervision (WTS), is unaffected by label noise and data distribution biases, albeit exhibits limited accuracy. Therefore, the activation of WTS is determined by evaluating the discrepancy between text-predicted labels and observed labels. Extensive experiments demonstrate the superior performance of WTS across synthetic and real-world datasets, particularly under high-noise conditions. The source code is available at https://anonymous.4open.science/r/WTS-0F3C.
title Learning from Imperfect Text Guidance: Robust Long-Tail Visual Recognition with High-Noise Label
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2604.23125