CoChat

Semi-Supervised Contrastive Learning With Similarity Co-Calibration

Open access
Zhang, Yuhang, Zhang, Xiaopeng, Li, Jie, Qiu, Robert C., Xu, Haohang, Tian, Qi · 2023 · IEEE Transactions on Multimedia

The DOI matches its Crossref record; 53 of the 54 references it cites were found in a registry or an index.

Abstract

Semi-supervised learning acts as an effective way to leverage massive unlabeled data. In this paper, we propose a novel training strategy, termed asSemi-supervised Contrastive Learning (SsCL), which combines the well-known contrastive loss in self-supervised learning with the cross entropy loss in semi-supervised learning, and jointly optimizes the two objectives in an end-to-end way. The highlight is that different from self-training based semi-supervised learning that conducts prediction and retraining over the same model weights, SsCL interchanges the predictions over the unlabeled data between the two branches, and thus formulates a co-calibration procedure, which we find is beneficial for better prediction and avoids being trapped in local minimum. Towards this goal, the contrastive loss branch models pairwise similarities among samples, using the pseudo labels generated from the cross entropy branch, and in turn calibrates the prediction distribution of the cross entropy branch with the contrastive similarity. We show that SsCL produces more discriminative representation and is beneficial to semi-supervised learning. Notably, on ImageNet with ResNet50 as the backbone, SsCL achieves$\bm {60.2\%}$and$\bm {72.1\%}$top-1 accuracy with 1% and 10% labeled samples respectively, which significantly outperforms the baseline, and is better than previous semi-supervised and self-supervised methods.

Overview

Integrity signals

Registry

Crossref · 10.1109/tmm.2022.3158069

Cites

53 of 53 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Citations

Cites

Show all 53 references

Research works printed but not linked: 1

  1. lee, 0, Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks, Proc Workshop Challenges Zrepresentation Learn, 3, 896

Cited by

See all 70

Metadata

Authors
Zhang, Y., Zhang, X., Li, J., Qiu, R. C., Xu, H., & Tian, Q.
Affiliations
  • Shanghai Jiao Tong University (CN)
  • Huawei Technologies (China) (CN)
Venue
IEEE Transactions on Multimedia
Published
2023
Volume
25
Pages
1749-1759
ISSN
  • 1520-9210 (ISSN-L)
  • 1941-0077
OpenAlex
W3162410350
Cited by
67
References
54
Citations by year
2026: 7 · 2025: 18 · 2024: 22 · 2023: 17
FWCI
4.94
Type
journal article
Language
en
Open access
Locations
  • IEEE Transactions on Multimedia (publishedVersion)
  • arXiv (Cornell University) (submittedVersion, cc-by)
  • arXiv (Cornell University) (cc-by)
Funders
  • National Key R & D Program of China (2018YFF0214705)
  • National Natural Science Foundation of China (61932014, 12141107)
  • National Key R&D Program of China (2020YFB1806700, BE2020026)
  • Key R&D Program of Jiangsu
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
  • Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Algorithms
  • Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Data Classification
Keywords
semi-supervised contrastive learning, contrastive loss, cross-entropy loss, pseudo-labeling, unlabeled data, joint optimization, self-supervised learning, representation learning, ImageNet, local optima avoidance

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Semi-Supervised Contrastive Learning With Similarity Co-Calibration. https://app.cochat.ai/papers/10.1109/tmm.2022.3158069
The paper
Zhang, Y., Zhang, X., Li, J., Qiu, R. C., Xu, H., & Tian, Q. (2023). Semi-Supervised Contrastive Learning With Similarity Co-Calibration. IEEE Transactions on Multimedia. https://doi.org/10.1109/tmm.2022.3158069

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.