Research map / Detection and segmentation / CNN features
ClassFormer: Exploring Class-Aware Dependency with Transformer for Medical Image Segmentation
Huimin Huang, Shiao Xie, Lanfen Lin, Ruofeng Tong, Yen-Wei Chen, Hong Wang, Yuexiang Li, Yawen Huang, Yefeng Zheng
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 ClassFormer to ResUNet (ablation) | ResUNet · Synapse | DSC: 78.69 -> 84.40 | Improved |
| Add the intra-class dynamic transformer (ablation) | ResUNet · Synapse | DSC: 78.69 -> 81.86 | Improved |
| Add Lbce supervision to the intra-class transformer (ablation) | ResUNet with intra-class transformer · Synapse | DSC: 81.86 -> 82.20 | Improved |
| Add the inter-class transformer (ablation) | ResUNet · Synapse | DSC: 78.69 -> 80.46 | Improved |
| Add class tokens to inter-class reasoning (ablation) | ResUNet with inter-class transformer · Synapse | DSC: 80.46 -> 82.77 | Improved |
| Add LEU to inter-class reasoning with class tokens (ablation) | ResUNet with inter-class transformer and class tokens · Synapse | DSC: 82.77 -> 83.07 | Improved |
| Arrange intra-class and inter-class transformers sequentially rather than in parallel (ablation) | ClassFormer · Synapse | DSC: 83.70 -> 83.74 | Improved |
| Use intra-class before inter-class reasoning (ablation) | Sequential ClassFormer · Synapse | DSC: 83.74 -> 84.40 | Improved |
| Add ClassFormer to U-Net (ablation) | U-Net · Synapse | DSC: 76.85 -> 83.89 | Improved |
| Add ClassFormer to TransUNet (ablation) | TransUNet · Synapse | DSC: 77.48 -> 81.25 | Improved |
| Add ClassFormer to SwinUNet (ablation) | SwinUNet · Synapse | DSC: 79.12 -> 80.59 | Improved |
| Use multi-scale salient-key selection (ablation) | Intra-class dynamic transformer · Synapse | DSC | Improved |
Closest papers by meaning
- Combinatorial CNN-Transformer Learning with Manifold Constraints for Semi-supervised Medical Image Segmentation (AAAI 2024 · similarity 0.88)
- Rethinking Decoders for Transformer-based Semantic Segmentation: A Compression Perspective (NeurIPS 2024 · similarity 0.87)
- DTMFormer: Dynamic Token Merging for Boosting Transformer-Based Medical Image Segmentation (AAAI 2024 · similarity 0.87)
- nnWNet: Rethinking the Use of Transformers in Biomedical Image Segmentation and Calling for a Unified Evaluation Benchmark (CVPR 2025 · similarity 0.87)
- A Simple Interpretable Transformer for Fine-Grained Image Classification and Analysis (ICLR 2024 · similarity 0.86)
- Learning Hierarchical Image Segmentation For Recognition and By Recognition (ICLR 2024 · similarity 0.86)
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.
