mlsanityData to 14 Oct 2026

Noisy Correspondence Learning with Meta Similarity Correction

arXiv 2304.06275 ↗First posted 13 Apr 2023cs.CV cs.MMcited by 26

Not on the map. Why?

Abstract (arXiv)

Despite the success of multimodal learning in cross-modal retrieval task, the remarkable progress relies on the correct correspondence among multimedia data. However, collecting such ideal data is expensive and time-consuming. In practice, most widely used datasets are harvested from the Internet and inevitably contain mismatched pairs. Training on such noisy correspondence datasets causes performance degradation because the cross-modal retrieval methods can wrongly enforce the mismatched data to be similar. To tackle this problem, we propose a Meta Similarity Correction Network (MSCN) to provide reliable similarity scores. We view a binary classification task as the meta-process that encourages the MSCN to learn discrimination from positive and negative meta-data. To further alleviate the influence of noise, we design an effective data purification strategy using meta-data as prior knowledge to remove the noisy samples. Extensive experiments are conducted to demonstrate the strengths of our method in both synthetic and real-world noises, including Flickr30K, MS-COCO, and Conceptual Captions.

Key facts. Cited by 26 papers in the map (data through 14 Oct 2026). Builds on 24 of its 47 references that are in the map. First posted on arXiv 13 Apr 2023.

Builds on

24 of 47 references.

References · 24

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  4. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,059
  5. 2017A Closer Look at Memorization in Deep Networkscited by 942
  6. 2017Learning to Generalize: Meta-Learning for Domain Generalizationcited by 763
  7. 2020DivideMix: Learning with Noisy Labels as Semi-supervised Learningcited by 692
  8. 2018Learning to Reweight Examples for Robust Deep Learningcited by 675
  9. 2018Stacked Cross Attention for Image-Text Matchingcited by 416
  10. 2018Bilevel Programming for Hyperparameter Optimization and Meta-Learningcited by 405
  11. 2019Unsupervised Label Noise Modeling and Loss Correctioncited by 328
  12. 2017Objects that Soundcited by 256
12 more
  1. 2019Visual Semantic Reasoning for Image-Text Matchingcited by 185
  2. 2018Learning to Learn from Noisy Labeled Datacited by 160
  3. 2015Learning Deep Structure-Preserving Image-Text Embeddingscited by 139
  4. 2021Similarity Reasoning and Filtration for Image-Text Matchingcited by 121
  5. 2020IMRAM: Iterative Matching with Recurrent Attention Memory for Cross-Modal Image-Text Retrievalcited by 115
  6. 2019Meta Label Correction for Noisy Label Learningcited by 108
  7. 2020Graph Structured Network for Image-Text Matchingcited by 93
  8. 2019Triplet-Based Deep Hashing Network for Cross-Modal Retrievalcited by 26
  9. 2015Learning to Answer Questions From Image Using Convolutional Neural Networkcited by 23
  10. 2019Image-Question-Answer Synergistic Network for Visual Dialogcited by 23
  11. 2018Cross-modal Embeddings for Video and Audio Retrievalcited by 21
  12. 2022Noise-Tolerant Learning for Audio-Visual Action Recognitioncited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 6; 2024: 11; 2025: 6; 2026: 3.

26 papers.

Sort:

By area:

  1. 2023Noisy-Correspondence Learning for Text-to-Image Person Re-identificationcited by 56
  2. 2024Multi-granularity Correspondence Learning from Long-term Noisy Videoscited by 34
  3. 2026INTENT: Invariance and Discrimination-aware Noise Mitigation for Robust Composed Image Retrievalcited by 26
  4. 2023Cross-modal Active Complementary Learning with Self-refining Correspondencecited by 22
  5. 2024The Synergy between Data and Multi-Modal Large Language Models: A Survey from Co-Development Perspectivecited by 15
  6. 2024Learning to Rematch Mismatched Pairs for Robust Cross-Modal Retrievalcited by 11
  7. 2024Mitigating Noisy Correspondence by Geometrical Structure Consistency Learningcited by 10
  8. 2023Negative Pre-aware for Noisy Cross-modal Matchingcited by 9
  9. 2023Noisy Pair Corrector for Dense Retrievalcited by 5
  10. 2023Noisy Correspondence Learning with Self-Reinforcing Errors Mitigationcited by 5
  11. 2024Semi-supervised Text-based Person Searchcited by 4
  12. 2024Disentangled Noisy Correspondence Learningcited by 4
14 more
  1. 2023CAPro: Webly Supervised Learning with Cross-Modality Aligned Prototypescited by 3
  2. 2024PC2: Pseudo-Classification Based Pseudo-Captioning for Noisy Correspondence Learning in Cross-Modal Retrievalcited by 3
  3. 2025ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learningcited by 3
  4. 2024AMNS: Attention-Weighted Selective Mask and Noise Label Suppression for Text-to-Image Person Retrievalcited by 2
  5. 2025TSVC:Tripartite Learning with Semantic Variation Consistency for Robust Image-Text Retrievalcited by 1
  6. 2025Multi-Modal Dataset Distillation in the Wildcited by 1
  7. 2025PCSR: Pseudo-label Consistency-Guided Sample Refinement for Noisy Correspondence Learningcited by 1
  8. 2024REPAIR: Rank Correlation and Noisy Pair Half-replacing with Memory for Noisy Correspondencecited by 0
  9. 2024Robust Noisy Correspondence Learning via Self-Drop and Dual-Weightcited by 0
  10. 2024CRoF: CLIP-based Robust Few-shot Learning on Noisy Labelscited by 0
  11. 2025Set a Thief to Catch a Thief: Combating Label Noise through Noisy Meta Learningcited by 0
  12. 2025PAUL: Uncertainty-Guided Partition and Augmentation for Robust Cross-View Geo-Localization under Noisy Correspondencecited by 0
  13. 2026Intra-Modal Neighbors Never Lie: Rectifying Inter-Modal Noisy Correspondence via Graph-Based Intra-Modal Reasoningcited by 0
  14. 2026Generative Retrieval for Unsupervised Text-Based Person Searchcited by 0