Research map / Detection and segmentation / Open-set and few-shot detection
Boosting Semantic Human Matting With Coarse Annotations
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use hybrid fine and coarse annotated training data instead of fine annotations alone (ablation) | Semantic human matting · Human matting test set (1360 images) | SAD: 0.0099 -> 0.0058 | Helped |
| Use hybrid fine and coarse annotated training data instead of fine annotations alone (ablation) | Semantic human matting · Human matting test set (1360 images) | MSE: 0.0067 -> 0.0026 | Helped |
| Use hybrid fine and coarse annotated training data instead of fine annotations alone (ablation) | Semantic human matting · Human matting test set (1360 images) | Gradient: 0.0029 -> 0.0016 | Helped |
| Use hybrid fine and coarse annotated training data instead of fine annotations alone (ablation) | Semantic human matting · Human matting test set (1360 images) | Connectivity: 0.0095 -> 0.0054 | Helped |
| Add the quality unification network (ablation) | Semantic human matting · Human matting test set (1360 images) | SAD: 0.0076 -> 0.0058 | Helped |
| Add the quality unification network (ablation) | Semantic human matting · Human matting test set (1360 images) | MSE: 0.0042 -> 0.0026 | Helped |
| Add the quality unification network (ablation) | Semantic human matting · Human matting test set (1360 images) | Gradient: 0.0024 -> 0.0016 | Helped |
| Add the quality unification network (ablation) | Semantic human matting · Human matting test set (1360 images) | Connectivity: 0.0072 -> 0.0054 | Helped |
| Use the proposed method rather than Trimap+DIM without providing trimaps | Semantic human matting · Human matting test set (1360 images) | SAD: 0.0045 vs 0.0058 | Hurt |
Closest papers by meaning
- Training Matting Models Without Alpha Labels (AAAI 2025 · similarity 0.89)
- MaSS13K: A Matting-level Semantic Segmentation Benchmark (CVPR 2025 · similarity 0.89)
- MaGGIe: Masked Guided Gradual Human Instance Matting (CVPR 2024 · similarity 0.88)
- MP-Mat: A 3D-and-Instance-Aware Human Matting and Editing Framework with Multiplane Representation (ICLR 2025 · similarity 0.87)
- Revisiting Context Aggregation for Image Matting (ICML 2024 · similarity 0.87)
- In-Context Matting (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.