Research map / Detection and segmentation / Open-set and few-shot detection
Incremental Few-Shot Instance Segmentation
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 incremental instance embeddings and cosine-similarity class representatives instead of MTFA fine-tuning for each novel class | iMTFA · COCO-Novel, 1-shot | detection AP: 2.47 -> 3.28 | Helped |
| Use incremental instance embeddings and cosine-similarity class representatives instead of MTFA fine-tuning for each novel class | iMTFA · COCO-Novel, 5-shot | segmentation AP: 6.62 -> 5.24 | Hurt |
| Use incremental instance embeddings and cosine-similarity class representatives instead of MTFA fine-tuning for each novel class | iMTFA · COCO-Split-2, 1-shot | segmentation AP: 6.7 -> 8.67 | Helped |
| Use incremental instance embeddings and cosine-similarity class representatives instead of MTFA fine-tuning for each novel class | iMTFA · COCO-Split-2, 5-shot | segmentation AP: 15.14 -> 12.33 | Hurt |
| Replace class-specific box and mask predictors with class-agnostic predictors (ablation) | MTFA · COCO-Novel, 5-shot | segmentation AP: 6.62 -> 6.11 | Hurt |
| Fine-tune the class-agnostic mask predictor (ablation) | CA MTFA · COCO-Novel, 5-shot | segmentation AP: 5.83 -> 6.11 | Helped |
| Add the second fine-tuning stage for the RoI feature extractor and classifier (ablation) | iMTFA · COCO-Novel, 5-shot | detection AP: 5.37 -> 6.19 | Helped |
| Add the second fine-tuning stage for the RoI feature extractor and classifier (ablation) | iMTFA · COCO-Novel, 5-shot | segmentation AP: 4.3 -> 5.22 | Helped |
| Increase cosine scaling factor from 1.0 to 15.0 (ablation) | iMTFA · COCO-All, 5-shot | detection AP, overall: — -> 19.67 | Helped |
| Increase cosine scaling factor from 1.0 to 15.0 (ablation) | iMTFA · COCO-All, 5-shot | detection AP, novel: — -> 5.62 | Hurt |
Closest papers by meaning
- iFS-RCNN: An Incremental Few-Shot Instance Segmenter (CVPR 2022 · similarity 0.93)
- FAPIS: A Few-Shot Anchor-Free Part-Based Instance Segmenter (CVPR 2021 · similarity 0.89)
- UniT: Unified Knowledge Transfer for Any-Shot Object Detection and Segmentation (CVPR 2021 · similarity 0.88)
- Training-Free Dataset Pruning for Instance Segmentation (ICLR 2025 · similarity 0.88)
- MaskDiff: Modeling Mask Distribution with Diffusion Probabilistic Model for Few-Shot Instance Segmentation (AAAI 2024 · similarity 0.87)
- The Devil is in the Object Boundary: Towards Annotation-free Instance Segmentation using Foundation Models (ICLR 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.