Contrastive Learning based Hybrid Networks for Long-Tailed Image Classification
The DOI matches its Crossref record; 36 of the 36 references it cites were found in a registry or an index.
Abstract
Learning discriminative image representations plays a vital role in long-tailed image classification because it can ease the classifier learning in imbalanced cases. Given the promising performance contrastive learning has shown recently in representation learning, in this work, we explore effective supervised contrastive learning strategies and tailor them to learn better image representations from imbalanced data in order to boost the classification accuracy thereon. Specifically, we propose a novel hybrid network structure being composed of a supervised contrastive loss to learn image representations and a cross-entropy loss to learn classifiers, where the learning is progressively transited from feature learning to the classifier learning to embody the idea that better features make better classifiers. We explore two variants of contrastive loss for feature learning, which vary in the forms but share a common idea of pulling the samples from the same class together in the normalized embedding space and pushing the samples from different classes apart. One of them is the recently proposed supervised contrastive (SC) loss, which is designed on top of the state-of-the-art unsupervised contrastive loss by incorporating positive samples from the same class. The other is a prototypical supervised contrastive (PSC) learning strategy which addresses the intensive memory consumption in standard SC loss and thus shows more promise under limited memory budget. Extensive experiments on three long-tailed classification datasets demonstrate the advantage of the proposed contrastive learning based hybrid networks in long-tailed classification.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
SMOTE synthetic minority over-sampling technique
Chawla, N. V., Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002) · Journal of Artificial Intelligence Research · doi:10.1613/jair.953 · Cited by 32,865
Focal Loss for Dense Object Detection
Lin, T.-Y., Goyal, P., Girshick, R., He, K., & Dollar, P. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.324 · Cited by 30,581
Learning Multiple Layers of Features from Tiny Images
Krizhevsky, A. (2024) · doi:10.57702/zp44cu3g · Cited by 23,395
Momentum Contrast for Unsupervised Visual Representation Learning
He, K., Fan, H., Wu, Y., Xie, S., & Girshick, R. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00975 · Cited by 13,347
A simple framework for contrastive learning of visual representations
Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020) · arXiv · doi:10.48550/arxiv.2002.05709 · Cited by 10,857
Supervised Contrastive Learning
Khosla, P., Teterwak, P., Wang, C., Sarna, A., Tian, Y., Isola, P., Maschinot, A., Liu, C., & Krishnan, D. (2020) · arXiv · doi:10.48550/arxiv.2004.11362 · Cited by 3,569 · cited 7×
“In SC learning [18], the distances to positives from the same class are contrasted with the distances to negatives from other classes, which results in memory consumption linear to the product of the positive size and negative size.”
BackgroundMethodInfluentialThe class imbalance problem: A systematic study1
Japkowicz, N., & Stephen, S. (2002) · Intelligent Data Analysis · doi:10.3233/ida-2002-6504 · Cited by 3,295
Class-Balanced Loss Based on Effective Number of Samples
Cui, Y., Jia, M., Lin, T.-Y., Song, Y., & Belongie, S. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00949 · Cited by 3,094 · cited 6×
“Typical methods include data re-sampling [1, 8, 35, 4, 28], loss re-weighting [26, 7, 30, 33], margin modification [3], and data augmentation [19, 6, 29].”
BackgroundMethodInfluentialA systematic study of the class imbalance problem in convolutional neural networks
Buda, M., Maki, A., & Mazurowski, M. A. (2018) · Neural Networks · doi:10.1016/j.neunet.2018.07.011 · Cited by 3,088 · cited 2×
“Typical methods include data re-sampling [1, 8, 35, 4, 28], loss re-weighting [26, 7, 30, 33], margin modification [3], and data augmentation [19, 6, 29].”
BackgroundMethod
Cited by
Deep Long-Tailed Learning: A Survey
Zhang, Y., Kang, B., Hooi, B., Yan, S., & Feng, J. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3268118 · Cited by 769
A survey on imbalanced learning: latest research, applications and future directions
Chen, W., Yang, K., Yu, Z., Shi, Y., & Chen, C. L. P. (2024) · Artificial Intelligence Review · doi:10.1007/s10462-024-10759-6 · Cited by 506
FedProc: Prototypical contrastive federated learning on non-IID data
Mu, X., Shen, Y., Cheng, K., Geng, X., Fu, J., Zhang, T., & Zhang, Z. (2023) · Future Generation Computer Systems · doi:10.1016/j.future.2023.01.019 · Cited by 274
Seeing What You Said: Talking Face Generation Guided by a Lip Reading Expert
Wang, J., Qian, X., Zhang, M., Tan, R. T., & Li, H. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01408 · Cited by 116
“Contrastive learning is a strategy to obtain more representative features and has widespread usage in various tasks, such as text-image retrieval [27], image classification [28] and acoustic event detection [29].”
BackgroundExploring Vision-Language Models for Imbalanced Learning
Wang, Y., Yu, Z., Wang, J., Heng, Q., Chen, H., Ye, W., Xie, R., Xie, X., & Zhang, S. (2023) · arXiv · doi:10.48550/arxiv.2304.01457 · Cited by 45
Metadata
- Authors
- Wang, P., Han, K., Wei, X.-S., Zhang, L., & Wang, L.
- Venue
- 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2021-06
- Pages
- 943-952
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W3175613352
- Cited by
- 294
- References
- 36
- FWCI
- 25.17
- Type
- conference paper
- Language
- en
- Open access
- closed
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
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.