paper-with-me

Domain Generalization 벤치마크

Domain Generalization on VLCS

74개 결과 · ⬇ CSV · JSON

Average Accuracy

74.46 77.22 79.98 82.74 85.5 2020-07 2026-09 RSC (AlexNet) — 75.43 (2020-07-05) RSC (AlexNet) — 75.43 (2020-07-05) DADG (ResNet-18) — 78.21 (2020-11-01) DADG (AlexNet) — 74.46 (2020-11-01) DADG (ResNet-18) — 78.21 (2020-11-01) DADG (AlexNet) — 74.46 (2020-11-01) SWAD (ResNet-50) — 79.1 (2021-02-17) SWAD (ResNet-50) — 79.1 (2021-02-17) StableNet (ResNet-18) — 77.65 (2021-04-16) StableNet (ResNet-18) — 77.65 (2021-04-16) Fishr (ResNet-50) — 78.2 (2021-09-07) Fishr (ResNet-50) — 78.2 (2021-09-07) Ensemble of Averages (RegNetY-16GF) — 81.1 (2021-10-21) Ensemble of Averages (ResNeXt-50 32x4d) — 80.4 (2021-10-21) Ensemble of Averages (ResNet-50) — 79.1 (2021-10-21) Ensemble of Averages (RegNetY-16GF) — 81.1 (2021-10-21) Ensemble of Averages (ResNeXt-50 32x4d) — 80.4 (2021-10-21) Ensemble of Averages (ResNet-50) — 79.1 (2021-10-21) AdaClust (ResNet-50, SWAD) — 79.6 (2021-12-09) AdaClust (ResNet-50) — 78.9 (2021-12-09) AdaClust (ResNet-50, SWAD) — 79.6 (2021-12-09) AdaClust (ResNet-50) — 78.9 (2021-12-09) DREAME — 79.02 (2021-12-17) DREAME — 79.02 (2021-12-17) SEDGE+ — 82.2 (2022-03-09) SEDGE — 79.8 (2022-03-09) SEDGE+ — 82.2 (2022-03-09) SEDGE — 79.8 (2022-03-09) MIRO (RegNetY-16GF, SWAD) — 81.7 (2022-03-21) MIRO (ResNet-50, SWAD) — 79.6 (2022-03-21) MIRO (RegNetY-16GF, SWAD) — 81.7 (2022-03-21) MIRO (ResNet-50, SWAD) — 79.6 (2022-03-21) CADG — 82.2 (2022-03-31) CADG — 82.2 (2022-03-31) GMoE-S/16 — 80.2 (2022-06-08) GMoE-S/16 — 80.2 (2022-06-08) CAR-FT (CLIP, ViT-B/16) — 85.5 (2022-11-29) CAR-FT (CLIP, ViT-B/16) — 85.5 (2022-11-29) D-Triplet(RegNetY-16GF) — 82.9 (2023-03-01) D-Triplet(Resnet-50) — 79.3 (2023-03-01) D-Triplet(RegNetY-16GF) — 82.9 (2023-03-01) D-Triplet(Resnet-50) — 79.3 (2023-03-01) VNE (ResNet-50, SWAD) — 79.7 (2023-04-04) VNE (ResNet-50, SWAD) — 79.7 (2023-04-04) SIMPLE+ — 82.7 (2023-05-01) SIMPLE — 79.9 (2023-05-01) SIMPLE+ — 82.7 (2023-05-01) SIMPLE — 79.9 (2023-05-01) POEM — 79.2 (2023-05-22) POEM — 79.2 (2023-05-22) PromptStyler (CLIP, ViT-B/16) — 82.9 (2023-07-27) PromptStyler (CLIP, ViT-L/14) — 82.4 (2023-07-27) PromptStyler (CLIP, ResNet-50) — 82.3 (2023-07-27) PromptStyler (CLIP, ViT-B/16) — 82.9 (2023-07-27) PromptStyler (CLIP, ViT-L/14) — 82.4 (2023-07-27) PromptStyler (CLIP, ResNet-50) — 82.3 (2023-07-27) VL2V-SD (CLIP, ViT-B/16) — 83.25 (2023-10-12) VL2V-SD (CLIP, ViT-B/16) — 83.25 (2023-10-12) UniDG + CORAL + ConvNeXt-B — 84.5 (2023-10-16) UniDG + CORAL + ConvNeXt-B — 84.5 (2023-10-16) MoA (OpenCLIP, ViT-B/16) — 83.1 (2023-10-17) MoA (OpenCLIP, ViT-B/16) — 83.1 (2023-10-17) GMDG (RegNetY-16GF) — 82.4 (2024-02-29) GMDG (RegNetY-16GF, SWAD) — 82.2 (2024-02-29) GMDG (ResNet-50, SWAD) — 79.6 (2024-02-29) GMDG (ResNet-50) — 79.2 (2024-02-29) GMDG (RegNetY-16GF) — 82.4 (2024-02-29) GMDG (RegNetY-16GF, SWAD) — 82.2 (2024-02-29) GMDG (ResNet-50, SWAD) — 79.6 (2024-02-29) GMDG (ResNet-50) — 79.2 (2024-02-29) SPG (CLIP, ResNet-50) — 84.0 (2024-04-30) SPG (CLIP, ViT-B/16) — 82.4 (2024-04-30) SPG (CLIP, ResNet-50) — 84.0 (2024-04-30) SPG (CLIP, ViT-B/16) — 82.4 (2024-04-30) RSC (AlexNet) — 75.43 (2020-07-05) DADG (ResNet-18) — 78.21 (2020-11-01) SWAD (ResNet-50) — 79.1 (2021-02-17) Ensemble of Averages (RegNetY-16GF) — 81.1 (2021-10-21) SEDGE+ — 82.2 (2022-03-09) CAR-FT (CLIP, ViT-B/16) — 85.5 (2022-11-29)
RankModel Average Accuracy PaperCodeYear
1 CAR-FT (CLIP, ViT-B/16) 85.5 Context-Aware Robust Fine-Tuning 2022
2 UniDG + CORAL + ConvNeXt-B 84.5 Towards Unified and Effective Domain Generalization invictus717/UniDG 2023
3 SPG (CLIP, ResNet-50) 84.0 Soft Prompt Generation for Domain Generalization renytek13/soft-prompt-generation-with-cgan 2024
4 VL2V-SD (CLIP, ViT-B/16) 83.25 Leveraging Vision-Language Models for Improving Domain Generalization in Image Classification val-iisc/VL2V-ADiP 2023
5 MoA (OpenCLIP, ViT-B/16) 83.1 Domain Generalization Using Large Pretrained Models with Mixture-of-Adapters KU-CVLAB/MoA 2023
6 D-Triplet(RegNetY-16GF) 82.9 Domain-aware Triplet loss in Domain Generalization workerbcd/dct 2023
6 PromptStyler (CLIP, ViT-B/16) 82.9 PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization zhanghr2001/promptta 2023
8 SIMPLE+ 82.7 SIMPLE: Specialized Model-Sample Matching for Domain Generalization microsoft/SeqML 2023
9 PromptStyler (CLIP, ViT-L/14) 82.4 PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization zhanghr2001/promptta 2023
9 GMDG (RegNetY-16GF) 82.4 Rethinking Multi-domain Generalization with A General Learning Objective zhaorui-tan/gmdg · zhaorui-tan/GMDG_cvpr2024 2024
9 SPG (CLIP, ViT-B/16) 82.4 Soft Prompt Generation for Domain Generalization renytek13/soft-prompt-generation-with-cgan 2024
12 PromptStyler (CLIP, ResNet-50) 82.3 PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization zhanghr2001/promptta 2023
13 SEDGE+ 82.2 Domain Generalization using Pretrained Models without Fine-tuning 2022
13 CADG 82.2 CADG: A Model Based on Cross Attention for Domain Generalization 2022
13 GMDG (RegNetY-16GF, SWAD) 82.2 Rethinking Multi-domain Generalization with A General Learning Objective zhaorui-tan/gmdg · zhaorui-tan/GMDG_cvpr2024 2024
16 MIRO (RegNetY-16GF, SWAD) 81.7 Domain Generalization by Mutual-Information Regularization with Pre-trained Models kakaobrain/miro 2022
17 Ensemble of Averages (RegNetY-16GF) 81.1 Ensemble of Averages: Improving Model Selection and Boosting Performance in Domain Generalization salesforce/ensemble-of-averages 2021
18 Ensemble of Averages (ResNeXt-50 32x4d) 80.4 Ensemble of Averages: Improving Model Selection and Boosting Performance in Domain Generalization salesforce/ensemble-of-averages 2021
19 GMoE-S/16 80.2 Sparse Mixture-of-Experts are Domain Generalizable Learners luodian/sf-moe-dg · KU-CVLAB/MoA 2022
20 SIMPLE 79.9 SIMPLE: Specialized Model-Sample Matching for Domain Generalization microsoft/SeqML 2023
1–20 / 74 다음 → 페이지당 10 20 50 100