Papers › Multi-Grained Contrast for Data-Efficient Unsupervised Representation Learning

Multi-Grained Contrast for Data-Efficient Unsupervised Representation Learning

2 Jul 2024arXiv:2407.02014archive 2025-07-28

Chengchao Shen, Jianzhong Chen, Jianxin Wang

The existing contrastive learning methods mainly focus on single-grained representation learning, e.g., part-level, object-level or scene-level ones, thus inevitably neglecting the transferability of representations on other granularity levels. In this paper, we aim to learn multi-grained representations, which can effectively describe the image on various granularity levels, thus improving generalization on extensive downstream tasks. To this end, we propose a novel Multi-Grained Contrast method (MGC) for unsupervised representation learning. Specifically, we construct delicate multi-grained correspondences between positive views and then conduct multi-grained contrast by the correspondences to learn more general unsupervised representations. Without pretrained on large-scale dataset, our method significantly outperforms the existing state-of-the-art methods on extensive downstream tasks, including object detection, instance segmentation, scene parsing, semantic segmentation and keypoint detection. Moreover, experimental results support the data-efficient property and excellent representation transferability of our method. The source code and trained weights are available at \url{https://github.com/visresearch/mgc}.

PaperPDFCode

Code

visresearch/mgc officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Contrastive LearningInstance SegmentationKeypoint DetectionObject DetectionRepresentation LearningScene ParsingSemantic Segmentationobject-detection

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Contrastive LearningFocus

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections