← Open-World Semi-Supervised Learning

Papers with Code · CC BY-SA 4.0

ImageNet-100 (TEMI Split)

아카이브 평가 5건 · 마지막 적재/변경 2026-10-30

원본 데이터셋 링크 1

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
SimGCD (ViT-B-16)	Seen accuracy (50% Labeled) 92.4 Novel accuracy (50% Labeled) 79.1 All accuracy (50% Labeled) 83.6	Parametric Classification for Generalized Category Discovery: A Baseline Study 2022-11-21	코드 1 · 코드 2
ORCA (ResNet-50)	Seen accuracy (50% Labeled) 89.1 Novel accuracy (50% Labeled) 72.1 All accuracy (50% Labeled) 77.8 Seen accuracy (10% Labeled) 83.9 Novel accuracy (10% Labeled) 60.5 All accuracy (10% Labeled) 69.7	Open-World Semi-Supervised Learning 2021-02-06	코드 1
OpenLDN (ResNet-50)	Seen accuracy (50% Labeled) 89.6 Novel accuracy (50% Labeled) 68.6 All accuracy (50% Labeled) 79.1	OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learning 2022-07-05	코드 1
GCD (ViT-B-16)	Seen accuracy (50% Labeled) 89.8 Novel accuracy (50% Labeled) 66.3 All accuracy (50% Labeled) 74.1	Generalized Category Discovery 2022-01-07	코드 1
TRSSL (ResNet-50)	Seen accuracy (10% Labeled) 82.6 Novel accuracy (10% Labeled) 67.8 All accuracy (10% Labeled) 75.4	Towards Realistic Semi-Supervised Learning 2022-07-05	코드 1