MaskCLIP: Masked Self-Distillation Advances Contrastive Language-Image Pretraining
Open accessThe DOI matches its Crossref record; 30 of the 30 references it cites were found in a registry or an index.
Abstract
This paper presents a simple yet effective framework MaskCLIP, which incorporates a newly proposed masked self-distillation into contrastive language-image pretraining. The core idea of masked self-distillation is to distill representation from a full image to the representation predicted from a masked image. Such incorporation enjoys two vital benefits. First, masked self-distillation targets local patch representation learning, which is complementary to vision-language contrastive focusing on text-related representation. Second, masked self-distillation is also consistent with vision-language contrastive from the perspective of training objective as both utilize the visual encoder for feature aligning, and thus is able to learn local semantics getting indirect supervision from the language. We provide specially designed experiments with a comprehensive analysis to validate the two benefits. Symmetrically, we also introduce the local semantic supervision into the text branch, which further improves the pretraining performance. With extensive experiments, we show that MaskCLIP, when applied to various challenging downstream tasks, achieves superior results in linear probing, finetuning, and zeroshot performance with the guidance of the language encoder. Code will be release at https://github.com/LightDXY/MaskCLIP.
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
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., & Guo, B. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00986 · Cited by 35,534
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372 · cited 1×
“As shown in Table 4, the 2nd team KLITE uses a strong Swin-B [46] as the backbone and additional knowledge from GPT-3 [5] and Wiktionary [52], and the 4th use the strong Focal-B [70] as the backbone, while our MaskCLIP greatly outperforms these methods with a simple ViT-B backbone and no additional knowledge.”
MethodLearning Transferable Visual Models From Natural Language Supervision
Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al. (2021) · arXiv · doi:10.48550/arxiv.2103.00020 · Cited by 15,293
Distilling the Knowledge in a Neural Network
Hinton, G., Vinyals, O., & Dean, J. (2015) · arXiv · doi:10.48550/arxiv.1503.02531 · Cited by 14,204
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
Decoupled Weight Decay Regularization
Loshchilov, I., & Hutter, F. (2017) · arXiv · doi:10.48550/arxiv.1711.05101 · Cited by 12,522
Masked Autoencoders Are Scalable Vision Learners
He, K., Chen, X., Xie, S., Li, Y., Dollar, P., & Girshick, R. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01553 · Cited by 8,489
Emerging Properties in Self-Supervised Vision Transformers
Caron, M., Touvron, H., Misra, I., Jegou, H., Mairal, J., Bojanowski, P., & Joulin, A. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00951 · Cited by 5,638
Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning
Grill, J.-B., Strub, F., Altché, F., Tallec, C., Richemond, P. H., Buchatskaya, E., Doersch, C., Pires, B. A., Guo, Z. D., Azar, M. G., et al. (2020) · arXiv · doi:10.48550/arxiv.2006.07733 · Cited by 3,846 · cited 3×
“Instead of bringing in an external teacher, selfdistillation methods such as [7, 28, 62] proposes using a mean teacher model that is derived from the student itself.”
BackgroundMethodExploring Simple Siamese Representation Learning
Chen, X., & He, K. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01549 · Cited by 3,725
LXMERT: Learning Cross-Modality Encoder Representations from Transformers
Tan, H., & Bansal, M. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1514 · Cited by 2,319 · cited 2×
“Vision-language pretraining Recent years have seen rapid progress made in vision-language pretraining [12, 16, 26, 27, 28, 29, 30, 31, 35, 36, 37, 40, 43, 44, 57].”
BackgroundMMDetection: Open MMLab Detection Toolbox and Benchmark
Chen, K., Wang, J., Pang, J., Cao, Y., Xiong, Y., Li, X., Sun, S., Feng, W., Liu, Z., Xu, J., et al. (2019) · arXiv · doi:10.48550/arxiv.1906.07155 · Cited by 2,227
Unified Perceptual Parsing for Scene Understanding
Xiao, T., Liu, Y., Zhou, B., Jiang, Y., & Sun, J. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01228-1_26 · Cited by 2,201
ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks
Lu, J., Batra, D., Parikh, D., & Lee, S. (2019) · arXiv · doi:10.48550/arxiv.1908.02265 · Cited by 2,109
UNITER: UNiversal Image-TExt Representation Learning
Chen, Y.-C., Li, L., Yu, L., El Kholy, A., Ahmed, F., Gan, Z., Cheng, Y., & Liu, J. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58577-8_7 · Cited by 2,055 · cited 1×
“Several multiple cross-modality loss functions have been proposed for the training objective, such as image-text matching [16, 40, 49, 61, 69], masked language modeling [16, 40, 49, 60, 61], masked image modeling [16, 49, 60, 61], contrastive loss [38, 41, 42].”
BackgroundScaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision
Jia, C., Yang, Y., Xia, Y., Chen, Y.-T., Parekh, Z., Pham, H., Le, Q. V., Sung, Y., Li, Z., & Duerig, T. (2021) · arXiv · doi:10.48550/arxiv.2102.05918 · Cited by 1,977
Conceptual Captions: A Cleaned, Hypernymed, Image Alt-text Dataset For Automatic Image Captioning
Sharma, P., Ding, N., Goodman, S., & Soricut, R. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p18-1238 · Cited by 1,879 · cited 2×
“We also investigate the performance on a smaller dataset CC3M [13] (we use ViT-B/16 here in coherency with previous experiments).”
MethodAn Empirical Study of Training Self-Supervised Vision Transformers
Chen, X., Xie, S., & He, K. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00950 · Cited by 1,648
The Role of Context for Object Detection and Semantic Segmentation in the Wild
Mottaghi, R., Chen, X., Liu, X., Cho, N.-G., Lee, S.-W., Fidler, S., Urtasun, R., & Yuille, A. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.119 · Cited by 1,438
VisualBERT: A Simple and Performant Baseline for Vision and Language
Li, L. H., Yatskar, M., Yin, D., Hsieh, C.-J., & Chang, K.-W. (2019) · arXiv · doi:10.48550/arxiv.1908.03557 · Cited by 1,198 · cited 2×
“Vision-language pretraining Recent years have seen rapid progress made in vision-language pretraining [12, 16, 26, 27, 28, 29, 30, 31, 35, 36, 37, 40, 43, 44, 57].”
BackgroundAlign before Fuse: Vision and Language Representation Learning with Momentum Distillation
Li, J., Selvaraju, R. R., Gotmare, A. D., Joty, S., Xiong, C., & Hoi, S. (2021) · arXiv · doi:10.48550/arxiv.2107.07651 · Cited by 1,078 · cited 2×
“Several multiple cross-modality loss functions have been proposed for the training objective, such as image-text matching [16, 40, 49, 61, 69], masked language modeling [16, 40, 49, 60, 61], masked image modeling [16, 49, 60, 61], contrastive loss [38, 41, 42].”
BackgroundUnified Vision-Language Pre-Training for Image Captioning and VQA
Zhou, L., Palangi, H., Zhang, L., Hu, H., Corso, J., & Gao, J. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i07.7005 · Cited by 864
Unicoder-VL: A Universal Encoder for Vision and Language by Cross-Modal Pre-Training
Li, G., Duan, N., Fang, Y., Gong, M., & Jiang, D. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i07.6795 · Cited by 795
Masked Feature Prediction for Self-Supervised Visual Pre-Training
Wei, C., Fan, H., Xie, S., Wu, C.-Y., Yuille, A., & Feichtenhofer, C. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01426 · Cited by 587
HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training
Li, L., Chen, Y.-C., Cheng, Y., Gan, Z., Yu, L., & Liu, J. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.161 · Cited by 408
Exploring Simple Siamese Representation Learning
Chen, X., & He, K. (2020) · arXiv · doi:10.48550/arxiv.2011.10566 · Cited by 381
BEVT: BERT Pretraining of Video Transformers
Wang, R., Chen, D., Wu, Z., Chen, Y., Dai, X., Liu, M., Jiang, Y.-G., Zhou, L., & Yuan, L. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01432 · Cited by 234
Self-citationE2E-VLP: End-to-End Vision-Language Pre-training Enhanced by Visual Learning
Xu, H., Yan, M., Li, C., Bi, B., Huang, S., Xiao, W., & Huang, F. (2021) · Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · doi:10.18653/v1/2021.acl-long.42 · Cited by 84
YFCC100M: The New Data in Multimedia Research
Thomee, B., Shamma, D. A., Friedland, G., Elizalde, B., Ni, K., Poland, D., Borth, D., & Li, L.-J. (2015) · arXiv · doi:10.48550/arxiv.1503.01817 · Cited by 69
Cited by
Foundation Models Defining a New Era in Vision: A Survey and Outlook
Awais, M., Naseer, M., Khan, S., Anwer, R. M., Cholakkal, H., Shah, M., Yang, M.-H., & Khan, F. S. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3506283 · Cited by 304
“Similarly, albeit with a different motivation, Dong et al. [67] argue that the language description of an image cannot express complete information as an image is a continuous and fine-grained signal.”
Metadata
- Authors
- Dong, X., Bao, J., Zheng, Y., Zhang, T., Chen, D., Yang, H., Zeng, M., Zhang, W., Yuan, L., Chen, D., Wen, F., & Yu, N.
- Venue
- 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2023-06
- Pages
- 10995-11005
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W4386075997
- Cited by
- 172
- References
- 30
- FWCI
- 19.56
- Type
- conference paper
- Language
- en
- Open access
- green
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.