Papers with Code · CC BY-SA 4.0

COCO-20i (1-shot)

아카이브 평가 85건 · 마지막 적재/변경 2026-10-30

평가 기록

과거 수집 기록이며 최신 순위가 아닙니다. 데이터셋 버전·split·실험 조건과 지표 방향이 검증되지 않은 결과는 직접 비교할 수 없습니다. 날짜는 논문 날짜이며 최신 평가일을 뜻하지 않습니다.

표가 화면보다 넓으면 좌우로 스크롤하여 논문과 구현 링크를 확인하세요.

원본 기록 순서 · 순위 미부여
모델	원본 지표·값	논문	구현
PGMA-Net (ResNet-101)	Mean IoU 59.4 FB-IoU 78.5	Visual and Textual Prior Guided Mask Assemble for Few-Shot Segmentation and Beyond 2023-08-15	연결 없음
GF-SAM (DINOv2)	Mean IoU 58.7	Bridge the Points: Graph-based Few-shot Segment Anything Semantically 2024-10-09	코드 1
SegGPT (ViT)	Mean IoU 56.1	SegGPT: Segmenting Everything In Context 2023-04-06	코드 1 · 코드 2 · 코드 3
PGMA-Net (ResNet-50)	Mean IoU 54.3 FB-IoU 75.8	Visual and Textual Prior Guided Mask Assemble for Few-Shot Segmentation and Beyond 2023-08-15	연결 없음
Matcher(DINOv2)	Mean IoU 52.7	Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching 2023-05-22	코드 1
DiffewS (SD2.1)	Mean IoU 52.2	Unleashing the Potential of the Diffusion Model in Few-shot Semantic Segmentation 2024-10-03	코드 1
HMNet (ResNet-50)	Mean IoU 52.1 FB-IoU 74.5	Hybrid Mamba for Few-Shot Segmentation 2024-09-29	코드 1
AENet (ResNet-50)	Mean IoU 51.3 FB-IoU 74.4	Eliminating Feature Ambiguity for Few-Shot Segmentation 2024-07-13	코드 1
DCAMA (Swin-B)	Mean IoU 50.9 FB-IoU 73.2	Dense Cross-Query-and-Support Attention Weighted Mask Aggregation for Few-Shot Segmentation 2022-07-18	코드 1
MSANet (ResNet-101)	Mean IoU 50.45 FB-IoU 51.09	MSANet: Multi-Similarity and Attention Guidance for Boosting Few-Shot Segmentation 2022-06-20	코드 1
HDMNet (ResNet-50)	Mean IoU 50 FB-IoU 72.2	Hierarchical Dense Correlation Distillation for Few-Shot Segmentation 2023-03-26	코드 1
VAT + MSI (ResNet-101)	Mean IoU 49.8	MSI: Maximize Support-Set Information for Few-Shot Segmentation 2022-12-09	코드 1
HMNet (VGG-16)	Mean IoU 49.1 FB-IoU 72.6	Hybrid Mamba for Few-Shot Segmentation 2024-09-29	코드 1
MSDNet (ResNet-101)	Mean IoU 48.5 FB-IoU 71.3 learnable parameters (million) 1.5	MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototyping 2024-09-17	코드 1
BAM (SVF, ResNet-50)	Mean IoU 48.47	Singular Value Fine-tuning: Few-shot Segmentation requires Few-parameters Fine-tuning 2022-06-13	코드 1
SCCAN (ResNet-101)	Mean IoU 48.2 FB-IoU 69.7	Self-Calibrated Cross Attention Network for Few-Shot Segmentation 2023-08-18	코드 1
PFENet (SVF, ResNet-50)	Mean IoU 48.02	Singular Value Fine-tuning: Few-shot Segmentation requires Few-parameters Fine-tuning 2022-06-13	코드 1
MIANet (ResNet-50)	Mean IoU 47.66 FB-IoU 71.51	MIANet: Aggregating Unbiased Instance and General Information for Few-Shot Semantic Segmentation 2023-05-23	코드 1
ProtoFormer (ResNet-101)	Mean IoU 47 FB-IoU 70	Prototype as Query for Few Shot Semantic Segmentation 2022-11-27	코드 1
FPTrans (DeiT-B/16)	Mean IoU 47	Feature-Proxy Transformer for Few-Shot Segmentation 2022-10-13	코드 1 · 코드 2
IPRNet (ResNet-101)	Mean IoU 46.9	Interclass Prototype Relation for Few-Shot Segmentation 2022-11-16	연결 없음
DGPNet (ResNet-101)	Mean IoU 46.7	Dense Gaussian Processes for Few-Shot Segmentation 2021-10-07	코드 1
HDMNet (DifFSS, ResNet-50)	Mean IoU 46.7	DifFSS: Diffusion Model for Few-Shot Semantic Segmentation 2023-07-03	코드 1
HSNet (HM, ResNet-101)	Mean IoU 46.5 FB-IoU 71.5	HM: Hybrid Masking for Few-Shot Segmentation 2022-03-24	코드 1
MSDNet (ResNet-50)	Mean IoU 46.5 FB-IoU 70.4 learnable parameters (million) 1.5	MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototyping 2024-09-17	코드 1
MSANet (ResNet-50)	Mean IoU 46.44 FB-IoU 48.03	MSANet: Multi-Similarity and Attention Guidance for Boosting Few-Shot Segmentation 2022-06-20	코드 1
AENet (VGG-16)	Mean IoU 46.4 FB-IoU 71.8	Eliminating Feature Ambiguity for Few-Shot Segmentation 2024-07-13	코드 1
SCCAN (ResNet-50)	Mean IoU 46.3 FB-IoU 69.9	Self-Calibrated Cross Attention Network for Few-Shot Segmentation 2023-08-18	코드 1
BAM (ResNet-50)	Mean IoU 46.23 learnable parameters (million) 26.7	Learning What Not to Segment: A New Perspective on Few-Shot Segmentation 2022-03-15	코드 1
ASNet (HM, ResNet-101)	Mean IoU 45.9 FB-IoU 71.1	HM: Hybrid Masking for Few-Shot Segmentation 2022-03-24	코드 1