Papers with Code · CC BY-SA 4.0

ADE20K-150

아카이브 평가 23건 · 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
Mask-Adapter	mIoU 38.2	Mask-Adapter: The Devil is in the Masks for Open-Vocabulary Segmentation 2024-12-05	코드 1
MaskCLIP++	mIoU 38.2	MaskCLIP++: A Mask-Based CLIP Fine-tuning Framework for Open-Vocabulary Image Segmentation 2024-12-16	코드 1
UMG-CLIP-E/14	mIoU 38.2	UMG-CLIP: A Unified Multi-Granularity Vision Generalist for Open-World Understanding 2024-01-12	코드 1
CAT-Seg	mIoU 37.9	CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation 2023-03-21	코드 1 · 코드 2 · 코드 3
SILC	mIoU 37.7	SILC: Improving Vision Language Pretraining with Self-Distillation 2023-10-20	연결 없음
MAFT+	mIoU 36.1	Collaborative Vision-Text Representation Optimizing for Open-Vocabulary Segmentation 2024-08-01	코드 1
UMG-CLIP-L/14	mIoU 36.1	UMG-CLIP: A Unified Multi-Granularity Vision Generalist for Open-World Understanding 2024-01-12	코드 1
OVSeg + OpenDAS	mIoU 35.8	OpenDAS: Open-Vocabulary Domain Adaptation for 2D and 3D Segmentation 2024-05-30	연결 없음
SED	mIoU 35.2	SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation 2023-11-27	코드 1
CLIPSelf	mIoU 34.5	CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction 2023-10-02	코드 1
FC-CLIP	mIoU 34.1	Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP 2023-08-04	코드 1
SCAN	mIoU 33.5	Open-Vocabulary Segmentation with Semantic-Assisted Calibration 2023-12-07	코드 1 · 코드 2
EBSeg-L	mIoU 32.8	Open-Vocabulary Semantic Segmentation with Image Embedding Balancing 2024-06-14	코드 1
MAFT-ViTL	mIoU 32.0	Learning Mask-aware CLIP Representations for Zero-Shot Segmentation 2023-09-30	코드 1 · 코드 2
PACL	mIoU 31.4	Open Vocabulary Semantic Segmentation with Patch Aligned Contrastive Learning 2022-12-09	코드 1
ODISE	mIoU 29.9	Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models 2023-03-08	코드 1
OVSeg Swin-B	mIoU 29.6	Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP 2022-10-09	코드 1
MaskCLIP	mIoU 23.7	Open-Vocabulary Universal Image Segmentation with MaskCLIP 2022-08-18	코드 1
POMP	mIoU 20.7	연결 없음 논문 날짜 미기재	연결 없음
SimSeg	mIoU 20.5	A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Model 2021-12-29	코드 1 · 코드 2
TTD (TCL)	mIoU 17.0	TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias 2024-03-30	코드 1
LaVG	mIoU 15.8	In Defense of Lazy Visual Grounding for Open-Vocabulary Semantic Segmentation 2024-08-09	코드 1
TTD (MaskCLIP)	mIoU 12.7	TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias 2024-03-30	코드 1