Papers with Code · CC BY-SA 4.0

ObjectNet

아카이브 평가 106건 · 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
ViT-B/16 (512x512) + Pixel	Top-1 Accuracy 47.53	Pyramid Adversarial Training Improves ViT Performance 2021-11-30	코드 1
AR-B (Opt Relevance)	Top-5 Accuracy 70 Top-1 Accuracy 47.1	Optimizing Relevance Maps of Vision Transformers Improves Robustness 2022-06-02	코드 1
BiT-M (ResNet-152x4)	Top-5 Accuracy 69 Top-1 Accuracy 47.0	Big Transfer (BiT): General Visual Representation Learning 2019-12-24	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7 · 코드 8 · 코드 9
ViT-B/16 (512x512)	Top-1 Accuracy 46.68	Pyramid Adversarial Training Improves ViT Performance 2021-11-30	코드 1
ViT-B (Discrete 512x512)	Top-1 Accuracy 46.62	Discrete Representations Strengthen Vision Transformer Robustness 2021-11-20	코드 1
AR-L	Top-5 Accuracy 68.3 Top-1 Accuracy 46.5	Optimizing Relevance Maps of Vision Transformers Improves Robustness 2022-06-02	코드 1
ViT-L (Opt Relevance)	Top-5 Accuracy 65.8 Top-1 Accuracy 43.2	Optimizing Relevance Maps of Vision Transformers Improves Robustness 2022-06-02	코드 1
CLIP L	Top-1 Accuracy 42.80	Optimal Representations for Covariate Shift 2021-12-31	코드 1 · 코드 2
ResNet-50 (JFT-300M)	Top-1 Accuracy 42.5	Billion-Scale Pretraining with Vision Transformers for Multi-Task Visual Representations 2021-08-12	연결 없음
ViT-B (Opt Relevance)	Top-5 Accuracy 65.1 Top-1 Accuracy 42.2	Optimizing Relevance Maps of Vision Transformers Improves Robustness 2022-06-02	코드 1
CLIP L (LAION)	Top-1 Accuracy 42.10	Optimal Representations for Covariate Shift 2021-12-31	코드 1 · 코드 2
AR-B	Top-5 Accuracy 63.7 Top-1 Accuracy 41.4	Optimizing Relevance Maps of Vision Transformers Improves Robustness 2022-06-02	코드 1
RegViT on 384x384 + Adv Pyramid	Top-1 Accuracy 39.79	Pyramid Adversarial Training Improves ViT Performance 2021-11-30	코드 1
ResNet-152 + GenInt with Transfer	Top-5 Accuracy 61.43 Top-1 Accuracy 39.38	Generative Interventions for Causal Learning 2020-12-22	코드 1
AR-S (Opt Relevance)	Top-5 Accuracy 61.7 Top-1 Accuracy 39.3	Optimizing Relevance Maps of Vision Transformers Improves Robustness 2022-06-02	코드 1
ResNet-50 (Bamboo)	Top-1 Accuracy 38.8	Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy 2022-03-15	코드 1 · 코드 2
RegViT on 384x384 + Adv Pixel	Top-1 Accuracy 37.41	Pyramid Adversarial Training Improves ViT Performance 2021-11-30	코드 1
ViT-L	Top-5 Accuracy 59.5 Top-1 Accuracy 37.4	Optimizing Relevance Maps of Vision Transformers Improves Robustness 2022-06-02	코드 1
DeiT-L (Opt Relevance)	Top-5 Accuracy 56.6 Top-1 Accuracy 36.3	Optimizing Relevance Maps of Vision Transformers Improves Robustness 2022-06-02	코드 1
BiT-S (ResNet-152x4)	Top-5 Accuracy 57 Top-1 Accuracy 36.0	Big Transfer (BiT): General Visual Representation Learning 2019-12-24	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7 · 코드 8 · 코드 9
NASNet-A	Top-5 Accuracy 56.05 Top-1 Accuracy 35.77	ObjectNet: A large-scale bias-controlled dataset for pushing the limits of object recognition models 2019-12-01	연결 없음
PNASNet-5L	Top-5 Accuracy 54.95 Top-1 Accuracy 35.63	ObjectNet: A large-scale bias-controlled dataset for pushing the limits of object recognition models 2019-12-01	연결 없음
RegViT on 384x384	Top-1 Accuracy 35.59	Pyramid Adversarial Training Improves ViT Performance 2021-11-30	코드 1
ViT-B	Top-5 Accuracy 56.4 Top-1 Accuracy 35.1	Optimizing Relevance Maps of Vision Transformers Improves Robustness 2022-06-02	코드 1
RegViT on 384x384 + Random Pyramid	Top-1 Accuracy 34.83	Pyramid Adversarial Training Improves ViT Performance 2021-11-30	코드 1
AR-S	Top-5 Accuracy 55.8 Top-1 Accuracy 34.3	Optimizing Relevance Maps of Vision Transformers Improves Robustness 2022-06-02	코드 1
RegViT on 384x384 + Random Pixel	Top-1 Accuracy 34.12	Pyramid Adversarial Training Improves ViT Performance 2021-11-30	코드 1
RegViT (RandAug) + Adv Pyramid	Top-1 Accuracy 32.92	Pyramid Adversarial Training Improves ViT Performance 2021-11-30	코드 1
Inception-v4	Top-5 Accuracy 51.98 Top-1 Accuracy 32.24	ObjectNet: A large-scale bias-controlled dataset for pushing the limits of object recognition models 2019-12-01	연결 없음
DeiT-S (Opt Relevance)	Top-5 Accuracy 53 Top-1 Accuracy 31.6	Optimizing Relevance Maps of Vision Transformers Improves Robustness 2022-06-02	코드 1