Research map / Detection and segmentation / Open-set and few-shot detection
CDICS: Delving Into Fine-Grained Attribute for In-Context Segmentation via Compositional Prompts and Phased Decoupling
Zhiyu Li, Dianmo Sheng, Qi Chu, Shilong Chen, Tao Gong, Zhou Wei, Nenghai Yu
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 Appearance Fusion module to the baseline (ablation) | CDICS baseline · ColorPACO | IoU: 50.3 -> 51.4 | Improved |
| add Appearance Fusion module to the baseline (ablation) | CDICS baseline · ColorPACO | FPR: 12.0 -> 9.3 | Improved |
| add decoupled two-stage training on top of Appearance Fusion (ablation) | CDICS · ColorPACO | IoU: 51.4 -> 58.9 | Improved |
| add decoupled two-stage training on top of Appearance Fusion (ablation) | CDICS · ColorPACO | FPR: 9.3 -> 5.7 | Improved |
| add decoupled two-stage training on top of Appearance Fusion (ablation) | CDICS · ColorPACO | AP50: 30.8 -> 42.4 | Improved |
| add compositional prompts and phased decoupling to SINE | SINE · ColorPACO | IoU: 44.1 -> 57.6 | Improved |
| add compositional prompts and phased decoupling to SINE | SINE · ColorPACO | FPR: 17.1 -> 3.9 | Improved |
| add compositional prompts and phased decoupling to SINE | SINE · COCO-20i | IoU: 64.5 -> 65.2 | No clear effect |
| add compositional prompts and phased decoupling to SINE | SINE · ColorPartImageNet (out-of-domain) | FPR: 23.4 -> 12.5 | Improved |
| add compositional prompts and phased decoupling to SINE | SINE · ColorPACO instance segmentation | AP: 14.3 -> 20.8 | Improved |
| compare against SegGPT on out-of-domain IoU | CDICS · ColorPartImageNet (out-of-domain) | IoU: 85.2 (SegGPT) vs 84.4 (CDICS) | Hurt |
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.
- SegGPT — SegGPT: Towards Segmenting Everything in Context (ICCV 2023) · better on 3 of 4 shared results
- PSALM — PSALM: Pixelwise Segmentation with Large Multi-modal Model (ECCV 2024) · 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
- A Simple Image Segmentation Framework via In-Context Examples (NeurIPS 2024 · similarity 0.89)
- UNICL-SAM: Uncertainty-Driven In-Context Segmentation with Part Prototype Discovery (CVPR 2025 · similarity 0.87)
- From Pixels to Concepts: Do Segmentation Models Understand What They Segment? (NeurIPS 2026 · similarity 0.87)
- Visual In-Context Prompting (CVPR 2024 · similarity 0.87)
- Explore In-Context Segmentation via Latent Diffusion Models (AAAI 2025 · similarity 0.87)
- Visual Prompting for Generalized Few-shot Segmentation: A Multi-scale Approach (CVPR 2024 · 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.
