One Leaf Reveals the Season: Occlusion-Based Contrastive Learning with Semantic-Aware Views for Efficient Visual Representation

Xiaoyu Yang, Lijian Xu, Hongsheng Li, Shaoting Zhang
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:71425-71440, 2025.

Abstract

This paper proposes a scalable and straightforward pre-training paradigm for efficient visual conceptual representation called occluded image contrastive learning (OCL). Our OCL approach is simple: we randomly mask patches to generate different views within an image and contrast them among a mini-batch of images. The core idea behind OCL consists of two designs. First, masked tokens have the potential to significantly diminish the conceptual redundancy inherent in images, and create distinct views with substantial fine-grained differences on the semantic concept level instead of the instance level. Second, contrastive learning is adept at extracting high-level semantic conceptual features during the pre-training, circumventing the high-frequency interference and additional costs associated with image reconstruction. Importantly, OCL learns highly semantic conceptual representations efficiently without relying on hand-crafted data augmentations or additional auxiliary modules. Empirically, OCL demonstrates high scalability with Vision Transformers, as the ViT-L/16 can complete pre-training in 133 hours using only 4 A100 GPUs, achieving 85.8% accuracy in downstream fine-tuning tasks. Code is available at https://github.com/XiaoyuYoung/OCL.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-yang25ao, title = {One Leaf Reveals the Season: Occlusion-Based Contrastive Learning with Semantic-Aware Views for Efficient Visual Representation}, author = {Yang, Xiaoyu and Xu, Lijian and Li, Hongsheng and Zhang, Shaoting}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {71425--71440}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/yang25ao/yang25ao.pdf}, url = {https://proceedings.mlr.press/v267/yang25ao.html}, abstract = {This paper proposes a scalable and straightforward pre-training paradigm for efficient visual conceptual representation called occluded image contrastive learning (OCL). Our OCL approach is simple: we randomly mask patches to generate different views within an image and contrast them among a mini-batch of images. The core idea behind OCL consists of two designs. First, masked tokens have the potential to significantly diminish the conceptual redundancy inherent in images, and create distinct views with substantial fine-grained differences on the semantic concept level instead of the instance level. Second, contrastive learning is adept at extracting high-level semantic conceptual features during the pre-training, circumventing the high-frequency interference and additional costs associated with image reconstruction. Importantly, OCL learns highly semantic conceptual representations efficiently without relying on hand-crafted data augmentations or additional auxiliary modules. Empirically, OCL demonstrates high scalability with Vision Transformers, as the ViT-L/16 can complete pre-training in 133 hours using only 4 A100 GPUs, achieving 85.8% accuracy in downstream fine-tuning tasks. Code is available at https://github.com/XiaoyuYoung/OCL.} }
Endnote
%0 Conference Paper %T One Leaf Reveals the Season: Occlusion-Based Contrastive Learning with Semantic-Aware Views for Efficient Visual Representation %A Xiaoyu Yang %A Lijian Xu %A Hongsheng Li %A Shaoting Zhang %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-yang25ao %I PMLR %P 71425--71440 %U https://proceedings.mlr.press/v267/yang25ao.html %V 267 %X This paper proposes a scalable and straightforward pre-training paradigm for efficient visual conceptual representation called occluded image contrastive learning (OCL). Our OCL approach is simple: we randomly mask patches to generate different views within an image and contrast them among a mini-batch of images. The core idea behind OCL consists of two designs. First, masked tokens have the potential to significantly diminish the conceptual redundancy inherent in images, and create distinct views with substantial fine-grained differences on the semantic concept level instead of the instance level. Second, contrastive learning is adept at extracting high-level semantic conceptual features during the pre-training, circumventing the high-frequency interference and additional costs associated with image reconstruction. Importantly, OCL learns highly semantic conceptual representations efficiently without relying on hand-crafted data augmentations or additional auxiliary modules. Empirically, OCL demonstrates high scalability with Vision Transformers, as the ViT-L/16 can complete pre-training in 133 hours using only 4 A100 GPUs, achieving 85.8% accuracy in downstream fine-tuning tasks. Code is available at https://github.com/XiaoyuYoung/OCL.
APA
Yang, X., Xu, L., Li, H. & Zhang, S.. (2025). One Leaf Reveals the Season: Occlusion-Based Contrastive Learning with Semantic-Aware Views for Efficient Visual Representation. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:71425-71440 Available from https://proceedings.mlr.press/v267/yang25ao.html.

Related Material