Research map / Detection and segmentation / Open-set and few-shot detection
Open-Vocabulary Camouflaged Object Segmentation
Youwei Pang, Xiaoqi Zhao, JiaMing Zuo, Lihe Zhang, Huchuan Lu
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 CamoPrompts template set (ablation) | OVCoser baseline · OVCamo | cIoU: 0.359 -> 0.383 | Improved |
| add semantic guidance (ablation) | OVCoser · OVCamo | cIoU: 0.383 -> 0.397 | Improved |
| add depth estimation auxiliary task (ablation) | OVCoser · OVCamo | cIoU: 0.397 -> 0.422 | Improved |
| add edge estimation auxiliary task (ablation) | OVCoser · OVCamo | cIoU: 0.397 -> 0.432 | Improved |
| use structure enhancement attention instead of simple addition fusion (ablation) | OVCoser · OVCamo | cIoU: 0.402 -> 0.436 | Improved |
| iterate refinement twice instead of once (ablation) | OVCoser · OVCamo | cIoU: 0.436 -> 0.443 | Improved |
| increase iterations from 2 to 3 (ablation) | OVCoser · OVCamo | cIoU: 0.443 -> 0.437 | No clear effect |
| add object-aware representation f_obj (ablation) | OVCoser · OVCamo | cIoU: 0.434 -> 0.443 | Improved |
| add correlation matrix M_cor guidance (ablation) | OVCoser · OVCamo | cIoU: 0.441 -> 0.443 | Improved |
| fine-tune COCO-trained OVSIS models on OVCamo | CAT-Seg · OVCamo | cIoU: 0.310 -> 0.088 | Hurt |
| add classification loss during training (ablation) | OVCoser · OVCamo | cS_m / cF_w: relative reductions of 8.6% and 15.7% | Hurt |
Closest papers by meaning
- Catch Me If You Can Describe Me: Open-Vocabulary Camouflaged Instance Segmentation with Diffusion (IJCV 2026 · similarity 0.93)
- Training-Free Open-Vocabulary Camouflaged Object Segmentation via Fine-Grained Object Binding and Adaptive Hybrid Prompt (CVPR 2026 · similarity 0.92)
- Seeing the Unseen: A Semantic Alignment and Context-Aware Prompt Framework for Open-Vocabulary Camouflaged Object Segmentation (ICCV 2025 · similarity 0.92)
- A Survey on Open-Vocabulary Detection and Segmentation: Past, Present, and Future (TPAMI 2024 · similarity 0.92)
- Distilling Spectral Graph for Object-Context Aware Open-Vocabulary Semantic Segmentation (CVPR 2025 · similarity 0.90)
- Emergent Open-Vocabulary Semantic Segmentation from Off-the-shelf Vision-Language Models (CVPR 2024 · similarity 0.90)
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.
