Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/EVA

EVA

Reported on 111 benchmarks across 15 tasks · 3 papers · 73 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Methodology65 results

3DonCOCO test-dev
APS· 2022-11-14
48.5
best: 48.6 (Focal-Stable-DINO (Focal-Huge, no TTA))
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
3DonCOCO-O
Average mAP· 2022-11-14
57.8
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
3DonCOCO-O
Effective Robustness· 2022-11-14
28.86
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
3DonCOCO minival
AP50· uses extra data· 2022-11-14
82.1
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
3DonCOCO minival
AP75· uses extra data· 2022-11-14
70.8
best: 71.4 (Focal-Stable-DINO (Focal-Huge, no TTA))
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
3DonCOCO minival
APL· uses extra data· 2022-11-14
78.5
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
3DonCOCO minival
APM· uses extra data· 2022-11-14
68.4
best: 68.5 (Focal-Stable-DINO (Focal-Huge, no TTA))
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
3DonCOCO minival
APS· uses extra data· 2022-11-14
49.4
best: 50.4 (Focal-Stable-DINO (Focal-Huge, no TTA))
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
3DonLVIS v1.0 val
box APr· uses extra data· 2022-11-14
55.1
best: 64 (Grounding DINO 1.5 Pro)
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
2D ClassificationonCOCO test-dev
AP50· 2022-11-14
81.9
best: 82.1 (Plain-DETR (Swin-L))
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
2D ClassificationonCOCO test-dev
AP75· 2022-11-14
71.7
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
2D ClassificationonCOCO test-dev
APL· 2022-11-14
77.9
best: 78 (Focal-Stable-DINO (Focal-Huge, no TTA))
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
2D ClassificationonCOCO test-dev
APM· 2022-11-14
67.7
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
2D ClassificationonCOCO test-dev
APS· 2022-11-14
48.5
best: 48.6 (Focal-Stable-DINO (Focal-Huge, no TTA))
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
2D ClassificationonCOCO-O
Average mAP· 2022-11-14
57.8
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
2D ClassificationonCOCO-O
Effective Robustness· 2022-11-14
28.86
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
2D ClassificationonCOCO minival
AP50· uses extra data· 2022-11-14
82.1
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
2D ClassificationonCOCO minival
AP75· uses extra data· 2022-11-14
70.8
best: 71.4 (Focal-Stable-DINO (Focal-Huge, no TTA))
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
2D ClassificationonCOCO minival
APL· uses extra data· 2022-11-14
78.5
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
2D ClassificationonCOCO minival
APM· uses extra data· 2022-11-14
68.4
best: 68.5 (Focal-Stable-DINO (Focal-Huge, no TTA))
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
2D ClassificationonCOCO minival
APS· uses extra data· 2022-11-14
49.4
best: 50.4 (Focal-Stable-DINO (Focal-Huge, no TTA))
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
2D ClassificationonLVIS v1.0 val
box APr· uses extra data· 2022-11-14
55.1
best: 64 (Grounding DINO 1.5 Pro)
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
2D Object DetectiononCOCO test-dev
AP50· 2022-11-14
81.9
best: 82.1 (Plain-DETR (Swin-L))
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
2D Object DetectiononCOCO test-dev
AP75· 2022-11-14
71.7
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
2D Object DetectiononCOCO test-dev
APL· 2022-11-14
77.9
best: 78 (Focal-Stable-DINO (Focal-Huge, no TTA))
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
2D Object DetectiononCOCO test-dev
APM· 2022-11-14
67.7
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
2D Object DetectiononCOCO test-dev
APS· 2022-11-14
48.5
best: 48.6 (Focal-Stable-DINO (Focal-Huge, no TTA))
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
2D Object DetectiononCOCO-O
Average mAP· 2022-11-14
57.8
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
2D Object DetectiononCOCO-O
Effective Robustness· 2022-11-14
28.86
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
2D Object DetectiononCOCO minival
AP50· uses extra data· 2022-11-14
82.1
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
2D Object DetectiononCOCO minival
AP75· uses extra data· 2022-11-14
70.8
best: 71.4 (Focal-Stable-DINO (Focal-Huge, no TTA))
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
2D Object DetectiononCOCO minival
APL· uses extra data· 2022-11-14
78.5
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
2D Object DetectiononCOCO minival
APM· uses extra data· 2022-11-14
68.4
best: 68.5 (Focal-Stable-DINO (Focal-Huge, no TTA))
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
2D Object DetectiononCOCO minival
APS· uses extra data· 2022-11-14
49.4
best: 50.4 (Focal-Stable-DINO (Focal-Huge, no TTA))
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
2D Object DetectiononLVIS v1.0 val
box APr· uses extra data· 2022-11-14
55.1
best: 64 (Grounding DINO 1.5 Pro)
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
16konCOCO test-dev
AP50· 2022-11-14
81.9
best: 82.1 (Plain-DETR (Swin-L))
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
16konCOCO test-dev
AP75· 2022-11-14
71.7
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
16konCOCO test-dev
APL· 2022-11-14
77.9
best: 78 (Focal-Stable-DINO (Focal-Huge, no TTA))
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
16konCOCO test-dev
APM· 2022-11-14
67.7
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
16konCOCO test-dev
APS· 2022-11-14
48.5
best: 48.6 (Focal-Stable-DINO (Focal-Huge, no TTA))
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
16konCOCO-O
Average mAP· 2022-11-14
57.8
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
16konCOCO-O
Effective Robustness· 2022-11-14
28.86
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
16konCOCO minival
AP50· uses extra data· 2022-11-14
82.1
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
16konCOCO minival
AP75· uses extra data· 2022-11-14
70.8
best: 71.4 (Focal-Stable-DINO (Focal-Huge, no TTA))
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
16konCOCO minival
APL· uses extra data· 2022-11-14
78.5
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
16konCOCO minival
APM· uses extra data· 2022-11-14
68.4
best: 68.5 (Focal-Stable-DINO (Focal-Huge, no TTA))
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
16konCOCO minival
APS· uses extra data· 2022-11-14
49.4
best: 50.4 (Focal-Stable-DINO (Focal-Huge, no TTA))
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
16konLVIS v1.0 val
box APr· uses extra data· 2022-11-14
55.1
best: 64 (Grounding DINO 1.5 Pro)
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
ChatbotonHarry Potter Dialogue Dataset
mauve· 2022-11-13
0.968
SOTA
Large Language Models Meet Harry Potter: A Bilingual Dataset for Aligning Dialogue Agents with Characters arXiv:2211.06869
3DonCOCO test-dev
AP50· 2022-11-14
81.9
best: 95 (ViTPose (ViTAE-G, ensemble))
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
3DonCOCO test-dev
AP75· 2022-11-14
71.7
best: 88.2 (ViTPose (ViTAE-G, ensemble))
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
3DonCOCO test-dev
APL· 2022-11-14
77.9
best: 86.5 (PoseBH-H)
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
3DonCOCO test-dev
APM· 2022-11-14
67.7
best: 83.8 (4xRSN-50 (ensemble))
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
3DonCOCO test-dev
box mAP· 2022-11-14
64.7
best: 66 (Co-DETR)
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
3DonCOCO minival
box AP· uses extra data· 2022-11-14
64.5
best: 66 (PE_spatial (DETA))
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
3DonLVIS v1.0 val
box AP· uses extra data· 2022-11-14
62.2
best: 68 (Co-DETR (single-scale))
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
2D ClassificationonCOCO test-dev
box mAP· 2022-11-14
64.7
best: 66 (Co-DETR)
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
2D ClassificationonCOCO minival
box AP· uses extra data· 2022-11-14
64.5
best: 66 (PE_spatial (DETA))
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
2D ClassificationonLVIS v1.0 val
box AP· uses extra data· 2022-11-14
62.2
best: 68 (Co-DETR (single-scale))
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
2D Object DetectiononCOCO test-dev
box mAP· 2022-11-14
64.7
best: 66 (Co-DETR)
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
2D Object DetectiononCOCO minival
box AP· uses extra data· 2022-11-14
64.5
best: 66 (PE_spatial (DETA))
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
2D Object DetectiononLVIS v1.0 val
box AP· uses extra data· 2022-11-14
62.2
best: 68 (Co-DETR (single-scale))
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
16konCOCO test-dev
box mAP· 2022-11-14
64.7
best: 66 (Co-DETR)
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
16konCOCO minival
box AP· uses extra data· 2022-11-14
64.5
best: 66 (PE_spatial (DETA))
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
16konLVIS v1.0 val
box AP· uses extra data· 2022-11-14
62.2
best: 68 (Co-DETR (single-scale))
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636

Computer Vision29 results

Object DetectiononCOCO test-dev
AP50· 2022-11-14
81.9
best: 82.1 (Plain-DETR (Swin-L))
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
Object DetectiononCOCO test-dev
AP75· 2022-11-14
71.7
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
Object DetectiononCOCO test-dev
APL· 2022-11-14
77.9
best: 78 (Focal-Stable-DINO (Focal-Huge, no TTA))
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
Object DetectiononCOCO test-dev
APM· 2022-11-14
67.7
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
Object DetectiononCOCO test-dev
APS· 2022-11-14
48.5
best: 48.6 (Focal-Stable-DINO (Focal-Huge, no TTA))
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
Object DetectiononCOCO-O
Average mAP· 2022-11-14
57.8
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
Object DetectiononCOCO-O
Effective Robustness· 2022-11-14
28.86
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
Object DetectiononCOCO minival
AP50· uses extra data· 2022-11-14
82.1
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
Object DetectiononCOCO minival
AP75· uses extra data· 2022-11-14
70.8
best: 71.4 (Focal-Stable-DINO (Focal-Huge, no TTA))
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
Object DetectiononCOCO minival
APL· uses extra data· 2022-11-14
78.5
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
Object DetectiononCOCO minival
APM· uses extra data· 2022-11-14
68.4
best: 68.5 (Focal-Stable-DINO (Focal-Huge, no TTA))
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
Object DetectiononCOCO minival
APS· uses extra data· 2022-11-14
49.4
best: 50.4 (Focal-Stable-DINO (Focal-Huge, no TTA))
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
Object DetectiononLVIS v1.0 val
box APr· uses extra data· 2022-11-14
55.1
best: 64 (Grounding DINO 1.5 Pro)
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
Instance SegmentationonCOCO test-dev
APL· uses extra data· 2022-11-14
72.4
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
Instance SegmentationonLVIS v1.0 val
mask AP· uses extra data· 2022-11-14
55
best: 60.7 (Co-DETR (single-scale))
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
VideoonKinetics-400
Acc@1· 2022-11-14
89.7
best: 93.6 (OmniVec2)
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
Object DetectiononCOCO test-dev
box mAP· 2022-11-14
64.7
best: 66 (Co-DETR)
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
Object DetectiononCOCO minival
box AP· uses extra data· 2022-11-14
64.5
best: 66 (PE_spatial (DETA))
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
Object DetectiononLVIS v1.0 val
box AP· uses extra data· 2022-11-14
62.2
best: 68 (Co-DETR (single-scale))
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
Instance SegmentationonCOCO minival
AP50· uses extra data· 2022-11-14
79.4
best: 80.1 (InternImage-H)
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
Instance SegmentationonCOCO minival
AP75· uses extra data· 2022-11-14
60.9
best: 62.8 (Co-DETR)
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
Instance SegmentationonCOCO minival
APL· uses extra data· 2022-11-14
72
best: 74.6 (Co-DETR)
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
Instance SegmentationonCOCO minival
APM· uses extra data· 2022-11-14
58.4
best: 59.7 (Co-DETR)
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
Instance SegmentationonCOCO minival
APS· uses extra data· 2022-11-14
37.6
best: 38.9 (Co-DETR)
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
Instance SegmentationonCOCO minival
mask AP· uses extra data· 2022-11-14
55
best: 56.6 (Co-DETR)
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
Instance SegmentationonCOCO test-dev
AP50· uses extra data· 2022-11-14
80
best: 80.8 (InternImage-H)
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
Instance SegmentationonCOCO test-dev
APM· uses extra data· 2022-11-14
58
best: 60.1 (Co-DETR)
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
Instance SegmentationonCOCO test-dev
APS· uses extra data· 2022-11-14
36.3
best: 41.6 (Co-DETR)
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
Instance SegmentationonCOCO test-dev
mask AP· uses extra data· 2022-11-14
55.5
best: 57.1 (Co-DETR)
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636

Knowledge Base6 results

Data Integrationondbp15k ja-en
Hits@1· uses extra data· 2020-09-28
0.762
best: 0.991 (MEAformer)
SOTA
Visual Pivoting for (Unsupervised) Entity Alignment arXiv:2009.13603
Data Integrationondbp15k fr-en
Hits@1· uses extra data· 2020-09-28
0.793
best: 0.996 (MEAformer)
SOTA
Visual Pivoting for (Unsupervised) Entity Alignment arXiv:2009.13603
Entity Alignmentondbp15k ja-en
Hits@1· uses extra data· 2020-09-28
0.762
best: 0.991 (MEAformer)
SOTA
Visual Pivoting for (Unsupervised) Entity Alignment arXiv:2009.13603
Entity Alignmentondbp15k fr-en
Hits@1· uses extra data· 2020-09-28
0.793
best: 0.996 (MEAformer)
SOTA
Visual Pivoting for (Unsupervised) Entity Alignment arXiv:2009.13603
Data IntegrationonDBP15k zh-en
Hits@1· uses extra data· 2020-09-28
0.761
best: 0.973 (MEAformer)
Visual Pivoting for (Unsupervised) Entity Alignment arXiv:2009.13603
Entity AlignmentonDBP15k zh-en
Hits@1· uses extra data· 2020-09-28
0.761
best: 0.973 (MEAformer)
Visual Pivoting for (Unsupervised) Entity Alignment arXiv:2009.13603

Medical4 results

Semantic SegmentationonCOCO-Stuff test
mIoU· 2022-11-14
53.4
best: 53.7 (VPNeXt)
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
Semantic SegmentationonADE20K val
mIoU· 2022-11-14
61.5
best: 62.8 (BEiT-3)
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
Semantic SegmentationonADE20K
Params (M)· uses extra data· 2022-11-14
1074
best: 3000 (FD-SwinV2-G)
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
Semantic SegmentationonADE20K
Validation mIoU· uses extra data· 2022-11-14
62.3
best: 63.6 (ViT-P (InternImage-H))
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636

Audio4 results

10-shot image generationonCOCO-Stuff test
mIoU· 2022-11-14
53.4
best: 53.7 (VPNeXt)
SOTA
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
10-shot image generationonADE20K val
mIoU· 2022-11-14
61.5
best: 62.8 (BEiT-3)
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
10-shot image generationonADE20K
Params (M)· uses extra data· 2022-11-14
1074
best: 3000 (FD-SwinV2-G)
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636
10-shot image generationonADE20K
Validation mIoU· uses extra data· 2022-11-14
62.3
best: 63.6 (ViT-P (InternImage-H))
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale arXiv:2211.07636

Speech1 result

DialogueonHarry Potter Dialogue Dataset
mauve· 2022-11-13
0.968
SOTA
Large Language Models Meet Harry Potter: A Bilingual Dataset for Aligning Dialogue Agents with Characters arXiv:2211.06869

Adversarial1 result

Text GenerationonHarry Potter Dialogue Dataset
mauve· 2022-11-13
0.968
SOTA
Large Language Models Meet Harry Potter: A Bilingual Dataset for Aligning Dialogue Agents with Characters arXiv:2211.06869

Natural Language Processing1 result

Dialogue GenerationonHarry Potter Dialogue Dataset
mauve· 2022-11-13
0.968
SOTA
Large Language Models Meet Harry Potter: A Bilingual Dataset for Aligning Dialogue Agents with Characters arXiv:2211.06869