{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/multi-level-contrastive-learning-for-dense","title":"Multi-Level Contrastive Learning for Dense Prediction Task","arxiv_id":"2304.02010","date":"2023-04-04","proceeding":null,"authors":["Qiushan Guo","Yizhou Yu","Yi Jiang","Jiannan Wu","Zehuan Yuan","Ping Luo"],"abstract":"In this work, we present Multi-Level Contrastive Learning for Dense Prediction Task (MCL), an efficient self-supervised method for learning region-level feature representation for dense prediction tasks. Our method is motivated by the three key factors in detection: localization, scale consistency and recognition. To explicitly encode absolute position and scale information, we propose a novel pretext task that assembles multi-scale images in a montage manner to mimic multi-object scenarios. Unlike the existing image-level self-supervised methods, our method constructs a multi-level contrastive loss that considers each sub-region of the montage image as a singleton. Our method enables the neural network to learn regional semantic representations for translation and scale consistency while reducing pre-training epochs to the same as supervised pre-training. Extensive experiments demonstrate that MCL consistently outperforms the recent state-of-the-art methods on various datasets with significant margins. In particular, MCL obtains 42.5 AP$^\\mathrm{bb}$ and 38.3 AP$^\\mathrm{mk}$ on COCO with the 1x schedule fintuning, when using Mask R-CNN with R50-FPN backbone pre-trained with 100 epochs. In comparison to MoCo, our method surpasses their performance by 4.0 AP$^\\mathrm{bb}$ and 3.1 AP$^\\mathrm{mk}$. Furthermore, we explore the alignment between pretext task and downstream tasks. We extend our pretext task to supervised pre-training, which achieves a similar performance to self-supervised learning. This result demonstrates the importance of the alignment between pretext task and downstream tasks, indicating the potential for wider applicability of our method beyond self-supervised settings.","url_abs":"https://arxiv.org/abs/2304.02010v1","url_pdf":"https://arxiv.org/pdf/2304.02010v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"multi-level-contrastive-learning-for-dense","repo_url":"https://github.com/guoqiushan/mcl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"}],"methods":[{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"infonce","method_name":"InfoNCE"},{"method_slug":"mask-r-cnn","method_name":"Mask R-CNN"},{"method_slug":"moco","method_name":"MoCo"},{"method_slug":"rpn","method_name":"RPN"},{"method_slug":"roi-align","method_name":"RoIAlign"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}