Research map / Detection and segmentation / Open-set and few-shot detection
Highly Accurate Dichotomous Image Segmentation
Xuebin Qin, Hang Dai, Xiaobin Hu, Deng-Ping Fan, Ling Shao, Luc Van Gool
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 |
|---|---|---|---|
| increase U2-Net input size from 320 to 512 (ablation) | U2-Net · DIS-VD | maxF_beta: 0.748 -> 0.769 | Improved |
| increase U2-Net input size to 1024 without adaptation (ablation) | U2-Net · DIS-VD | maxF_beta: 0.769 -> .764 | Mixed |
| add stride-2 input convolution (Adp) at 1024 input (ablation) | U2-Net · DIS-VD | maxF_beta: .764 -> 0.776 | Improved |
| add intermediate supervision on last 6 decoder stages with L2 (ablation) | IS-Net · DIS-VD | maxF_beta: 0.776 -> 0.790 | Improved |
| add intermediate supervision on last 6 decoder stages with L2 (ablation) | IS-Net · DIS-VD | HCE_gamma: 1076 -> 1056 | Improved |
| apply intermediate supervision only to last 1 decoder stage (ablation) | IS-Net · DIS-VD | maxF_beta: 0.776 -> 0.777 | Improved |
| use L2 instead of KL for feature synchronization (ablation) | IS-Net · DIS-VD | maxF_beta: 0.770 -> 0.790 | Improved |
| use L2 instead of L1 for feature synchronization (ablation) | IS-Net · DIS-VD | HCE_gamma: 1144 -> 1056 | Improved |
| use separate outconvs instead of sharing with GT encoder (ablation) | IS-Net · DIS-VD | maxF_beta: 0.745 -> 0.790 | Improved |
| choose GT encoder seed 5289 over seed 1 (ablation) | IS-Net · DIS-VD | maxF_beta: 0.786 -> 0.791 | No clear effect |
| choose GT encoder seed 5289 over seed 472 (ablation) | IS-Net · DIS-VD | HCE_gamma: 1071 -> 1116 | Hurt |
| use IS-Net instead of U2-Net | IS-Net · DIS-VD | HCE_gamma: 1413 -> 1116 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- BASNet — BASNet: Boundary-Aware Salient Object Detection (CVPR 2019) · better on 4 of 4 shared results
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
- Multi-view Aggregation Network for Dichotomous Image Segmentation (CVPR 2024 · similarity 0.90)
- MaskFactory: Towards High-quality Synthetic Data Generation for Dichotomous Image Segmentation (NeurIPS 2024 · similarity 0.88)
- High-Precision Dichotomous Image Segmentation via Probing Diffusion Capacity (ICLR 2025 · similarity 0.87)
- Uncertainty-aware Fine-tuning of Segmentation Foundation Models (NeurIPS 2024 · similarity 0.86)
- COCONut: Modernizing COCO Segmentation (CVPR 2024 · similarity 0.85)
- Learning Hierarchical Image Segmentation For Recognition and By Recognition (ICLR 2024 · similarity 0.85)
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.
