Research map / Detection and segmentation / Open-set and few-shot detection
InterFormer: Real-time Interactive Image Segmentation
You Huang, Hao Yang, Ke Sun, Shengchuan Zhang, Liujuan Cao, Guannan Jiang, Rongrong Ji
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 |
|---|---|---|---|
| replace vanilla FPN-like click fusion with I-MSA (ablation) | InterFormer ViT-B · SBD (40k iterations) | NoC90: 10.70 -> 8.27 | Improved |
| replace RITM click simulation with simplified simulation (ablation) | InterFormer ViT-B-I-MSA-Light · SBD (40k iterations) | NoC90: 8.27 -> 8.34 | No clear effect |
| use ViT-Large backbone instead of ViT-Base (ablation) | InterFormer I-MSA-Light · SBD (40k iterations) | NoC90: 8.34 -> 7.71 | Improved |
| add zoom-in strategy to deeper I-MSA blocks of InterFormer-Tiny (ablation) | InterFormer-Tiny · SBD | NoC90 and PIE: NoC90 5.51 -> 5.89; PIE 18.9 -> 15.9 | Mixed |
| InterFormer-Tiny versus FocalClick-SegFormerB3-S2 on DAVIS | interactive segmentation · DAVIS | NoC90: 5.21 vs 4.90 | Hurt |
| preprocess images offline with ViT and decode with lightweight I-MSA instead of SimpleClick-ViT-L | interactive segmentation pipeline · SBD | SPC and NoC90: SPC 3.33 -> 0.50; NoC90 4.89 -> 5.51 | Improved |
Closest papers by meaning
- A Simple Image Segmentation Framework via In-Context Examples (NeurIPS 2024 · similarity 0.86)
- CFR-ICL: Cascade-Forward Refinement with Iterative Click Loss for Interactive Image Segmentation (AAAI 2024 · similarity 0.86)
- FocSAM: Delving Deeply into Focused Objects in Segmenting Anything (CVPR 2024 · similarity 0.86)
- Interactive Medical Image Segmentation: A Benchmark Dataset and Baseline (CVPR 2025 · similarity 0.86)
- Rethinking Interactive Image Segmentation with Low Latency High Quality and Diverse Prompts (CVPR 2024 · similarity 0.86)
- TETRIS: Towards Exploring the Robustness of Interactive Segmentation (AAAI 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.
