Incremental Few-Shot Semantic Segmentation Via Multi-Level Switchable Visual Prompts
Maoxian Wan, Kaige Li, Qichuan Geng, Weimin Shi, Zhong Zhou
2025Year
1Citations
Abstract
trophic forgetting and reducing increasing computation.
Our method achieves new state-of-the-art performance, outperforming previous SoTA methods by 30.28% mIoU-N on VOC and 13.90% mIoU-N on COCO under 1-shot. Code is available at https://github.com/WanMotion/MSVP.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Builds on17
- An Image is Worth 16x16 Words: Transformers for Image Recognition at ScaleAlexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn et al.ICLR 2021 · 21,477 citations
- BEiT: BERT Pre-Training of Image TransformersHangbo Bao, Li Dong, Songhao Piao, Furu WeiICLR 2022 · 3,632 citations
- Learning to Prompt for Continual LearningZifeng Wang, Zizhao Zhang, Chen-Yu Lee, Han Zhang et al.CVPR 2022 · 635 citations
- GroupViT: Semantic Segmentation Emerges from Text SupervisionJiarui Xu, Shalini De Mello, Sifei Liu, Wonmin Byeon et al.CVPR 2022 · 398 citations
- Forward Compatible Few-Shot Class-Incremental LearningDa-Wei Zhou, Fu-Yun Wang, Han-Jia Ye, Liang Ma et al.CVPR 2022 · 259 citations
Related papers
- BoxInst: High-Performance Instance Segmentation With Box AnnotationsZhi Tian, Chunhua Shen, Xinlong Wang, Hao ChenCVPR 2021
- SOLOv2: Dynamic and Fast Instance SegmentationXinlong Wang, Rufeng Zhang, Tao Kong, Lei Li et al.NeurIPS 2020 · 1,193 citations
- MetaPortrait: Identity-Preserving Talking Head Generation with Fast Personalized AdaptationBowen Zhang, Chenyang Qi, Pan Zhang, Bo Zhang et al.CVPR 2023
- Human-Centric Multi-Exposure Fusion: Benchmark and Bi-level Cognition Distillation FrameworkJingjie Shang, Tengyu Ma, Heng Zhang, Jinyuan Liu et al.CVPR 2026
- SwiftNet: Real-Time Video Object SegmentationHaochen Wang, Xiaolong Jiang, Haibing Ren, Yao Hu et al.CVPR 2021
