Research map / Detection and segmentation / Open-set and few-shot detection
Active Image Segmentation Propagation
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 active selection that combines influence, diversity, and uncertainty instead of passive random annotation | Segmentation propagation · ImageNet and MIT Object Discovery | Segmentation accuracy | Helped |
| Use active selection that combines influence, diversity, and uncertainty instead of PageRank selection | Segmentation propagation · ImageNet and MIT Object Discovery | Segmentation accuracy | Helped |
| Add uncertainty-based image selection (ablation) | Active segmentation propagation · ImageNet and MIT Object Discovery | Segmentation accuracy | Helped |
| Add filtered, diverse region proposals rather than using top objectness proposals (ablation) | Joint foreground segmentation · MIT Object Discovery | MABO: 64.95 -> 72.2 | Helped |
| Add careful region-proposal filtering (ablation) | Weakly supervised joint segmentation · MIT Object Discovery | Jaccard score: 8% | Helped |
| Use active segmentation propagation rather than Semantic Propagation | ImageNet segmentation propagation · 99,020 common images across 352 classes | Jaccard score: 62.63% -> 65% | Helped |
| Reduce the annotation budget using active selection rather than the passive propagation baseline | Segmentation propagation · ImageNet | Human-annotated data needed for equivalent accuracy: 26% less | Helped |
Closest papers by meaning
- Large-Scale Interactive Object Segmentation With Human Annotators (CVPR 2019 · similarity 0.88)
- Box-Level Active Detection (CVPR 2023 · similarity 0.88)
- The Emergence of Objectness: Learning Zero-shot Segmentation from Videos (NeurIPS 2021 · similarity 0.87)
- FOCUS: Towards Universal Foreground Segmentation (AAAI 2025 · similarity 0.86)
- BLADE: Box-Level Supervised Amodal Segmentation through Directed Expansion (AAAI 2024 · similarity 0.86)
- Diffusion-Driven Two-Stage Active Learning for Low-Budget Semantic Segmentation (NeurIPS 2025 · 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.