AI Paper Atlas

Research map / Benchmarks / ISIC 5-shot

ISIC 5-shot leaderboard

11 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on ISIC 5-shot. Best mIoU: 79.8 (DCDNet, AAAI 2026).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

ISIC 5-shot · mIoU

11 papers, each with its best reported number for its own method; higher is better.

#mIoU ↑MethodPaperTopic
179.8DCDNet
ResNet-50
Divide-and-Conquer Decoupled Network for Cross-Domain Few-Shot Segmentation
AAAI 2026 · Table 1
Domain adaptation and generalization
272.2GPRN
ResNet-50
SAM-Aware Graph Prompt Reasoning Network for Cross-Domain Few-Shot Segmentation
AAAI 2025 · Table 1
Open-set and few-shot detection
370.3DATO
ResNet-50
Dual-Agent Optimization framework for Cross-Domain Few-Shot Segmentation
CVPR 2025 · Table 1
Domain adaptation and generalization
469.8IFA T=3
Res-50
Cross-Domain Few-Shot Segmentation via Iterative Support-Query Correspondence Mining
CVPR 2024 · Table 1
Zero-/few-shot and meta-learning
562.55Ours (training-free)
DINOv3-B
Training-free Cross-domain Few-shot Segmentation via Robust Semantic Representation and Matching
ECCV 2026 · Table 1
Domain adaptation and generalization
659.11CAV-SAM
SAM2-tiny
Correspondence as Video: Test-Time Adaption on SAM2 for Reference Segmentation in the Wild
ICCV 2025 · Table 1
Video segmentation and tracking
755.2Ours
DINOv2 ViT-L/14 + SAM ViT-H
Bridge the Points: Graph-based Few-shot Segment Anything Semantically
NeurIPS 2024 · Table 2
Open-set and few-shot detection
855.02SDRC
ViT-B
Self-Disentanglement and Re-Composition for Cross-Domain Few-Shot Segmentation
ICML 2025 · Table 1
Domain adaptation and generalization
953.98APSeg
SAM ViT-base
APSeg: Auto-Prompt Network for Cross-Domain Few-Shot Semantic Segmentation
CVPR 2024 · Table 1
Zero-/few-shot and meta-learning
1053.3ABCDFSS
ResNet50 (ImageNet-pretrained)
Adapt Before Comparison: A New Perspective on Cross-Domain Few-Shot Segmentation
CVPR 2024 · Table 2
Zero-/few-shot and meta-learning
1 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.