Research map / Label-efficient and robust learning / Self-supervised and contrastive
SERE: Exploring Feature Self-Relation for Self-Supervised Transformer
Zhong-Yu Li, Shanghua Gao, Ming‐Ming Cheng
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add SERE | DINO ViT-S/16 · ImageNet-1K fine-tuning | Top-1: 79.7 -> 80.9 | Improved |
| add SERE | iBOT ViT-S/16 · ImageNet-1K fine-tuning | Top-1: 80.9 -> 81.5 | Improved |
| add SERE | iBOT ViT-B/16 · ImageNet-1K fine-tuning | Top-1: 83.3 -> 83.7 | Improved |
| add SERE | DINO ViT-S/16 · ImageNet-1K 1% labels | Top-1: 52.1 -> 55.9 | Improved |
| add SERE | DINO ViT-S/16 · ImageNet-S pretrained init | mIoU: 35.1 -> 36.9 | Improved |
| add SERE | DINO ViT-S/16 · PASCAL VOC segmentation | mIoU: 77.1 -> 79.7 | Improved |
| add SERE | DINO ViT-S/16 · COCO detection | box AP: 46.0 -> 46.6 | Improved |
| add SERE | DINO ViT-S/16 · CIFAR-10 transfer | Top-1: 98.8 -> 98.9 | Improved |
| add SERE | DINO ResNet-50 · PASCAL VOC (ImageNet-S300 pretrain) | mIoU: 61.6 -> 62.5 | Improved |
| add spatial self-relation to image-level embedding (ablation) | DINO · ImageNet-S300 pretrain, PASCAL VOC | mIoU: 68.1 -> 70.7 | Improved |
| add channel self-relation to image-level embedding (ablation) | DINO · ImageNet-S300 pretrain, PASCAL VOC | mIoU: 68.1 -> 69.8 | Improved |
| add channel self-relation and L_I to spatial self-relation (ablation) | SERE · ImageNet-S300 pretrain, PASCAL VOC | mIoU: 71.5 -> 73.5 | Improved |
Closest papers by meaning
- An Empirical Study of Training Self-Supervised Vision Transformers (ICCV 2021 · similarity 0.90)
- Efficient Self-supervised Vision Transformers for Representation Learning (ICLR 2022 · similarity 0.88)
- Vision Transformers Need Registers (ICLR 2024 · similarity 0.87)
- A Theoretical Analysis of Self-Supervised Learning for Vision Transformers (ICLR 2025 · similarity 0.87)
- DeiT III: Revenge of the ViT (ECCV 2022 · similarity 0.87)
- Self-supervised Models are Good Teaching Assistants for Vision Transformers (ICML 2022 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
