.png){kind=icon}
.png){kind=icon}
Return
Multi-grained contrast for data-efficient unsupervised representation learning
.png){kind=icon}
OA
AI
DOI：10.1016/j.patcog.2025.111655.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The existing contrastive learning methods mainly focus on single-grained representation learning, 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 pretraining on large-scale dataset, our method significantly outperforms the existing state-ofthe-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 https://github.com/visresearch/mgc.
Keywords:
Unsupervised learning
Representation learning
Deep learning
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
7.6
Papers:
1.3W
Citations:
4.5W
Organization
No organization information available