Research map / Architectures and efficiency / Attention and transformers
Anti-Oversmoothing in Deep Vision Transformers via the Fourier Domain Analysis: From Theory to Practice
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 AttnScale | DeiT-S, 12 layers · ImageNet-1k val | top-1 accuracy (%): 79.8 -> 80.7 | Helped |
| Add FeatScale | DeiT-S, 12 layers · ImageNet-1k val | top-1 accuracy (%): 79.8 -> 80.9 | Helped |
| Add AttnScale | DeiT-S, 24 layers · ImageNet-1k val | top-1 accuracy (%): 80.5 -> 81.1 | Helped |
| Add FeatScale | DeiT-S, 24 layers · ImageNet-1k val | top-1 accuracy (%): 80.5 -> 81.3 | Helped |
| Add AttnScale | CaiT-S, 24 layers · ImageNet-1k val | top-1 accuracy (%): 82.6 -> 83.2 | Helped |
| Add FeatScale | CaiT-S, 24 layers · ImageNet-1k val | top-1 accuracy (%): 82.6 -> 83.2 | Helped |
| Add AttnScale | Swin-S, 24 layers · ImageNet-1k val | top-1 accuracy (%): 83.0 -> 83.4 | Helped |
| Add FeatScale | Swin-S, 24 layers · ImageNet-1k val | top-1 accuracy (%): 83.0 -> 83.5 | Helped |
Closest papers by meaning
- You Only Need Less Attention at Each Stage in Vision Transformers (CVPR 2024 · similarity 0.91)
- Alias-Free ViT: Fractional Shift Invariance via Linear Attention (NeurIPS 2025 · similarity 0.89)
- Bi-ViT: Pushing the Limit of Vision Transformer Quantization (AAAI 2024 · similarity 0.89)
- LF-ViT: Reducing Spatial Redundancy in Vision Transformer for Efficient Image Recognition (AAAI 2024 · similarity 0.88)
- Skip-Attention: Improving Vision Transformers by Paying Less Attention (ICLR 2024 · similarity 0.88)
- Unveil Benign Overfitting for Transformer in Vision: Training Dynamics, Convergence, and Generalization (NeurIPS 2024 · similarity 0.88)
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.