AI Paper Atlas

Research map / Benchmarks / COCO-20i 1-shot

COCO-20i 1-shot leaderboard

33 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on COCO-20i 1-shot. Best mIoU: 71.33 (DSV-LFS, CVPR 2025).

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.

COCO-20i 1-shot · mIoU

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

#mIoU ↑MethodPaperTopic
171.33DSV-LFS
LLaVA-v1.5-7B + SAM
DSV-LFS: Unifying LLM-Driven Semantic Cues with Visual Features for Robust Few-Shot Segmentation
CVPR 2025 · Table 1
Open-set and few-shot detection
261.2GFSAM+GSM
DINOv2 ViT-L/14 + SAM ViT-H
Training-free Boosting for Few-shot Segmentation via Generalizing Semantic Mining
AAAI 2026 · Table 1
Open-set and few-shot detection
360.3LDIS-1
SD 1.5
Explore In-Context Segmentation via Latent Diffusion Models
AAAI 2025 · 1-shot segmentation table
Autoregressive and latent generation
458.7Ours
DINOv2 ViT-L/14 + SAM ViT-H
Bridge the Points: Graph-based Few-shot Segment Anything Semantically
NeurIPS 2024 · Table 1
Open-set and few-shot detection
557.2SegGPT w/ SCS (Ours)
SegGPT (pre-trained weights)
Rethinking and Improving Visual Prompt Selection for In-Context Learning Segmentation Framework
ECCV 2024 · Table 1
Open-set and few-shot detection
656.8ours-PI-CLIP (HDMNet)
HDMNet
Rethinking Prior Information Generation with CLIP for Few-Shot Segmentation
CVPR 2024 · Table 2
CLIP and zero-shot
753.9LLaFS
CodeLlama-7B
LLaFS: When Large Language Models Meet Few-Shot Segmentation
CVPR 2024 · Table 1
Language, safety and interpretability
853.7DeFSS
ResNet50
DeFSS: Image-to-Mask Denoising Learning for Few-shot Segmentation
ICCV 2025 · Table 2
Open-set and few-shot detection
951.5OCNet
ResNet-50
Object-level Correlation for Few-Shot Segmentation
ICCV 2025 · Table 2
Open-set and few-shot detection
1050.9DCAMA
Swin-B
Dense Cross-Query-and-Support Attention Weighted Mask Aggregation for Few-Shot Segmentation
ECCV 2022 · Table 1
Open-set and few-shot detection
23 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.