• Home
  • Search
  • Screening, Rectifying, and Re-Screening: A Unified Framework for Tuning Vision-Language Models with Noisy Labels
  • https://doi.org/10.24963/ijcai.2025/568Copy DOI Icon

Screening, Rectifying, and Re-Screening: A Unified Framework for Tuning Vision-Language Models with Noisy Labels

  • Sep 1, 2025
  • Chaowei Fang +5 more
Show More
  • Abstract
  • Literature Map
  • Similar Papers
Abstract

Pre-trained vision-language models have shown remarkable potential for downstream tasks. However, their fine-tuning under noisy labels remains an open problem due to challenges like self-confirmation bias and the limitations of conventional small-loss criteria. In this paper, we propose a unified framework to address these issues, consisting of three key steps: Screening, Rectifying, and Re-Screening. First, a dual-level semantic matching mechanism is introduced to categorize samples into clean, ambiguous, and noisy samples by leveraging both macro-level and micro-level textual prompts. Second, we design tailored pseudo-labeling strategies to rectify noisy and ambiguous labels, enabling their effective incorporation into the training process. Finally, a re-screening step, utilizing cross-validation with an auxiliary vision-language model, mitigates self-confirmation bias and enhances the robustness of the framework. Extensive experiments across ten datasets demonstrate that the proposed method significantly outperforms existing approaches for tuning vision-language pre-trained models with noisy labels.

Similar Papers
  • PDF
  • Research Article
  • Citations3

Separating hard clean samples from noisy samples with samples’ learning risk for DNN when learning with noisy labels

  • Mar 01, 2024
  • Complex & Intelligent Systems
  • Lihui Deng +5
  • Research Article
  • Citations4

Agree to Disagree: Robust Anomaly Detection with Noisy Labels

  • Feb 10, 2025
  • Proceedings of the ACM on Management of Data
  • Dennis M Hofmann +6
  • Conference Article
  • Citations1

Distribution Mining and Noise Correction for Facial Expression Recognition

  • Apr 19, 2024
  • Hailan Huang +1
  • Research Article
  • Citations16

Skin Lesion Segmentation in Dermoscopic Images with Noisy Data.

  • Apr 05, 2023
  • Journal of digital imaging
  • Norsang Lama +4
  • Research Article
  • Citations6

Enhancing Sample Utilization in Noise-robust Deep Metric Learning with Subgroup-based Positive-pair Selection.

  • Jan 01, 2024
  • IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
  • Zhipeng Yu +4
  • Research Article

FedEBM: Robust graph federated learning via energy-based model.

  • May 28, 2026
  • Neural networks : the official journal of the International Neural Network Society
  • Jiayu Wang +4
  • Research Article
  • Citations2

Learning from Noisy Labels via Self-Taught On-the-Fly Meta Loss Rescaling

  • Apr 11, 2025
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Michael Heck +8
  • Research Article
  • Citations6

APPN: An Attention-based Pseudo-label Propagation Network for few-shot learning with noisy labels

  • Jul 23, 2024
  • Neurocomputing
  • Jiaqi Chen +5
  • PDF
  • Research Article
  • Citations4

CRAS: Curriculum Regularization and Adaptive Semi-Supervised Learning with Noisy Labels

  • Jan 31, 2024
  • Applied Sciences
  • Ryota Higashimoto +2
  • Research Article
  • Citations4

Imbalanced Medical Image Segmentation With Pixel-Dependent Noisy Labels.

  • May 01, 2025
  • IEEE transactions on medical imaging
  • Erjian Guo +3
  • Research Article
  • Citations9

TC-Net: Detecting Noisy Labels Via Transform Consistency

  • Jan 01, 2022
  • IEEE Transactions on Multimedia
  • Rumeng Yi +1
  • Research Article
  • Citations9

A robust intelligent fault diagnosis method for rotating machinery under noisy labels

  • Sep 21, 2023
  • Measurement Science and Technology
  • Chengyuan Chen +4
  • Research Article
  • Citations5

Noise is the fatal poison: A Noise-aware Network for noisy dataset classification

  • Oct 11, 2023
  • Neurocomputing
  • Xiaotian Yu +5
  • Research Article
  • Citations11

Learning with noisy labels using collaborative sample selection and contrastive semi-supervised learning

  • Apr 27, 2024
  • Knowledge-Based Systems
  • Qing Miao +6
  • Research Article

A Progressive Deep Neural Network Training Method for Image Classification with Noisy Labels

  • Dec 12, 2022
  • Applied Sciences
  • Xuguo Yan +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.