Name
Abstract | ||
|---|---|---|
ABSTRACTSelf-supervised representation learning for visual pre-training has achieved remarkable success with sample (instance or pixel) discrimination and semantics discovery of instance, whereas there still exists a non-negligible gap between pre-trained model and downstream dense prediction tasks. Concretely, these downstream tasks require more accurate representation, in other words, the pixels from the same object must belong to a shared semantic category, which is lacking in the previous methods. In this work, we present Dense Semantic Contrast (DSC) for modeling semantic category decision boundaries at a dense level to meet the requirement of these tasks. Furthermore, we propose a dense cross-image semantic contrastive learning framework for multi-granularity representation learning. Specially, we explicitly explore the semantic structure of the dataset by mining relations among pixels from different perspectives. For intra-image relation modeling, we discover pixel neighbors from multiple views. And for inter-image relations, we enforce pixel representation from the same semantic class to be more similar than the representation from different classes in one mini-batch. Experimental results show that our DSC model outperforms state-of-the-art methods when transferring to downstream dense prediction tasks, including object detection, semantic segmentation, and instance segmentation. Code will be made available. |
Year | DOI | Venue |
|---|---|---|
2021 | 10.1145/3474085.3475551 | International Multimedia Conference |
DocType | Citations | PageRank |
Conference | 0 | 0.34 |
References | Authors | |
0 | 8 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Xiaoni Li | 1 | 0 | 1.35 |
| Yu Zhou | 2 | 98 | 22.73 |
| Yifei Zhang | 3 | 1 | 3.06 |
| Aoting Zhang | 4 | 0 | 0.68 |
| Wei Wang | 5 | 0 | 0.34 |
| Ning Jiang | 6 | 0 | 1.01 |
| Haiying Wu | 7 | 0 | 0.34 |
| Weiping Wang | 8 | 7 | 9.20 |