摘要: Recent advances in self-supervised contrastive learning yield good image-level representation, which favors classification tasks but usually neglects pixel-level detailed information, leading to unsatisfactory transfer performance... 展开
作者 | Feng Wang Huiyu Wang Chen Wei Alan Yuille Wei Shen | ||
---|---|---|---|
作者单位 | |||
文集名称 | Computer Vision – ECCV 2022 | ||
出版年 | 2022 | ||
会议名称 | European Conference on Computer Vision | ||
卷/页码 | Part 30 / 499-515 | 开始页/总页数 | 00000499 / 17 |
会议地点 | Tel Aviv(IL) | 会议年/会议届次 | 2022 / 17th |
关键词 | Dense contrastive learning Semantic segmentation | ||
馆藏号 | P2300516 |