Research map / Detection and segmentation / Open-set and few-shot detection
CoHD: A Counting-Aware Hierarchical Decoding Framework for Generalized Referring Expression Segmentation
Zhuoyan Luo, Yinghao Wu, Tianheng Cheng, Yong Liu, Yicheng Xiao, Hongfa Wang, Xiao-Ping Zhang, Yujiu Yang
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 Hierarchical Semantic Decoder (HSD) (ablation) | CoHD baseline · gRefCOCO val (Swin-T) | cIoU: 56.55 -> 60.67 | Improved |
| add Adaptive Object Counting (AOC) (ablation) | CoHD baseline · gRefCOCO val (Swin-T) | cIoU: 56.55 -> 58.56 | Improved |
| add AOC on top of HSD (ablation) | CoHD · gRefCOCO val (Swin-T) | gIoU: 63.15 -> 65.89 | Improved |
| add Query Refinement (ablation) | HSD · gRefCOCO val (Swin-T) | gIoU: 63.31 -> 65.89 | Improved |
| add Dynamic Hierarchical Aggregation (ablation) | HSD · gRefCOCO val (Swin-T) | gIoU: 62.77 -> 65.89 | Improved |
| add intra-selection to inter-selection (ablation) | DHA · gRefCOCO val (Swin-T) | gIoU: 64.03 -> 65.89 | Improved |
| add inter-selection to intra-selection (ablation) | DHA · gRefCOCO val (Swin-T) | gIoU: 63.56 -> 65.89 | Improved |
| use count head instead of binary head for object existence (ablation) | CoHD · gRefCOCO val (Swin-T) | N-acc.: 56.09 -> 60.95 | Improved |
| use binary head instead of count head: counting accuracy (ablation) | CoHD · gRefCOCO val (Swin-T) | C-acc.: 72.73 -> 75.45 | Improved |
| add AOC as auxiliary task with binary head (ablation) | HSD · gRefCOCO val (Swin-T) | gIoU: 63.15 -> 63.72 | Improved |
| replace deep supervision with dynamic hierarchical aggregation (ablation) | CoHD · gRefCOCO val (Swin-T) | gIoU: 64.11 -> 65.89 | Improved |
| add deep supervision on top of DHA (ablation) | CoHD · gRefCOCO val (Swin-T) | gIoU: 65.89 -> 63.35 | Hurt |
Closest papers by meaning
- RefDetector: A Simple Yet Effective Matching-based Method for Referring Expression Comprehension (AAAI 2025 · similarity 0.89)
- Hierarchical Alignment-enhanced Adaptive Grounding Network for Generalized Referring Expression Comprehension (AAAI 2025 · similarity 0.89)
- Unveiling Parts Beyond Objects: Towards Finer-Granularity Referring Expression Segmentation (CVPR 2024 · similarity 0.89)
- Rethinking Two-Stage Referring Expression Comprehension: A Novel Grounding and Segmentation Method Modulated by Point (AAAI 2024 · similarity 0.89)
- GSVA: Generalized Segmentation via Multimodal Large Language Models (CVPR 2024 · similarity 0.88)
- Ref-Adv: Exploring MLLM Visual Reasoning in Referring Expression Tasks (ICLR 2026 · similarity 0.88)
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.
