Research map / Detection and segmentation / Open-set and few-shot detection
Mitigating Pose–Scale Discrepancy Bias and Reforming Multi-Support Reasoning for Few-Shot Semantic Segmentation
Shreya Biswas, Zhaozheng Yin
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 the disentangled autoencoder (DAE) to the baseline (ablation) | DMNet · PASCAL-5i 5-shot (ResNet-50) | mIoU: 62.2 -> 75.0 | Improved |
| add cyclic ensemble refinement on top of DAE (ablation) | DMNet · PASCAL-5i 5-shot (ResNet-50) | mIoU: 75.0 -> 76.8 | Improved |
| add spatially adaptive fusion on top of DAE (ablation) | DMNet · PASCAL-5i 5-shot (ResNet-50) | mIoU: 75.0 -> 76.6 | Improved |
| add both cyclic ensemble and spatial fusion to DAE (ablation) | DMNet · PASCAL-5i 5-shot (ResNet-50) | mIoU: 75.0 -> 77.5 | Improved |
| add reconstruction loss Lrec (ablation) | DMNet · PASCAL-5i 1-shot (ResNet-50) | mIoU: 68.9 -> 69.8 | Improved |
| add semantic consistency loss Lsem (ablation) | DMNet · PASCAL-5i 1-shot (ResNet-50) | mIoU: 69.8 -> 71.7 | Improved |
| add equivariance loss Lec (ablation) | DMNet · PASCAL-5i 1-shot (ResNet-50) | mIoU: 71.7 -> 74.7 | Improved |
| add geometric pointer regression loss Lgeo (ablation) | DMNet · PASCAL-5i 1-shot (ResNet-50) | mIoU: 74.7 -> 76.1 | Improved |
| add cyclic ensemble refinement to DAE (accuracy vs latency) (ablation) | DMNet · 1-shot avg mIoU / inference time | avg mIoU: 68.0 -> 69.2 (14.3 ms -> 15.9 ms) | Improved |
| add spatially adaptive fusion to DAE+Cyclic (accuracy vs latency) (ablation) | DMNet · 1-shot avg mIoU / inference time | avg mIoU: 69.2 -> 70.8 (15.9 ms -> 19.7 ms) | Improved |
| replace frozen ResNet-50 backbone with frozen SAM encoder | DMNet · Avg of PASCAL-5i and COCO-20i 1/5-shot | avg mIoU: 68.4 -> 70.8 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- DeFSS — DeFSS: Image-to-Mask Denoising Learning for Few-shot Segmentation (ICCV 2025) · better on 8 of 8 shared results
- SANSA — SANSA: Unleashing the Hidden Semantics in SAM2 for Few-Shot Segmentation (NeurIPS 2025) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Geometry-Guided Semantic Reconstruction for 3D Instance Segmentation (NeurIPS 2026 · similarity 0.89)
- Unlocking the Potential of Pre-trained Vision Transformers for Few-Shot Semantic Segmentation through Relationship Descriptors (CVPR 2024 · similarity 0.88)
- Bridge the Points: Graph-based Few-shot Segment Anything Semantically (NeurIPS 2024 · similarity 0.87)
- Label-Efficient Few-Shot Semantic Segmentation with Unsupervised Meta-Training (AAAI 2024 · similarity 0.87)
- Bidirectional Reciprocative Information Communication for Few-Shot Semantic Segmentation (ICML 2024 · similarity 0.87)
- DSV-LFS: Unifying LLM-Driven Semantic Cues with Visual Features for Robust Few-Shot Segmentation (CVPR 2025 · 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.
