Research map / Detection and segmentation / CNN features
CycleMLP: A MLP-like Architecture for Dense Prediction
Shoufa Chen, Enze Xie, Chongjian GE, Runjian Chen, Ding Liang, Ping Luo
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 |
|---|---|---|---|
| Replace a 7×1 branch with a 1×7 branch to retain both directional branches (ablation) | CycleMLP-B2 · ImageNet-1K val | Top-1 accuracy: 80.4 -> 81.6 | Improved |
| Add the 1×1 branch to the 1×7 and 7×1 branches (ablation) | CycleMLP-B2 · ImageNet-1K val | Top-1 accuracy: 81.3 -> 81.6 | Improved |
| Replace the 7×1 branch with a second 1×7 branch (ablation) | CycleMLP-B2 · ImageNet-1K val | Top-1 accuracy: 81.6 -> 80.6 | Hurt |
| Replace the 1×7 branch with a second 7×1 branch (ablation) | CycleMLP-B2 · ImageNet-1K val | Top-1 accuracy: 81.6 -> 80.5 | Hurt |
| Use stepsize 3 instead of 7 (ablation) | CycleMLP-B2 · ImageNet-1K val | Top-1 accuracy: 81.6 -> 81.6 | No clear effect |
| Use stepsize 3 instead of 7 (ablation) | CycleMLP-B2 · ADE20K val | mIoU: 43.9 -> 42.4 | Hurt |
| Use stepsize 5 instead of 7 (ablation) | CycleMLP-B2 · ImageNet-1K val | Top-1 accuracy: 81.6 -> 81.6 | No clear effect |
| Use stepsize 5 instead of 7 (ablation) | CycleMLP-B2 · ADE20K val | mIoU: 43.9 -> 43.2 | Hurt |
| Use stepsize 9 instead of 7 (ablation) | CycleMLP-B2 · ImageNet-1K val | Top-1 accuracy: 81.6 -> 81.5 | Hurt |
| Use stepsize 9 instead of 7 (ablation) | CycleMLP-B2 · ADE20K val | mIoU: 43.9 -> 43.2 | Hurt |
| Use cyclical rather than random sampling (ablation) | CycleMLP · ImageNet-1K | Top-1 accuracy: +1.3% | Improved |
| Use dilated rather than random sampling (ablation) | CycleMLP · ImageNet-1K | Top-1 accuracy: +1.0% acc | Improved |
Closest papers by meaning
- CycleMLP: A MLP-Like Architecture for Dense Visual Predictions (TPAMI 2023 · similarity 0.99)
- MorphMLP: An Efficient MLP-Like Backbone for Spatial-Temporal Representation Learning (ECCV 2022 · similarity 0.86)
- RepMLPNet: Hierarchical Vision MLP With Re-Parameterized Locality (CVPR 2022 · similarity 0.85)
- M2Det: A Single-Shot Object Detector Based on Multi-Level Feature Pyramid Network (AAAI 2019 · similarity 0.85)
- AS-MLP: An Axial Shifted MLP Architecture for Vision (ICLR 2022 · similarity 0.85)
- MLP-Mixer: An all-MLP Architecture for Vision (NeurIPS 2021 · similarity 0.84)
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.
