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/MAT

MAT

Reported on 26 benchmarks across 4 tasks · 2 papers · 10 SOTA

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

Medical18 results

Image GenerationonPlaces2
P-IDS· 2022-03-29
23.42
best: 28.7 (ASUKA)
SOTA
MAT: Mask-Aware Transformer for Large Hole Image Inpainting arXiv:2203.15270
Image GenerationonPlaces2
U-IDS· 2022-03-29
38.34
best: 41.3 (ASUKA)
SOTA
MAT: Mask-Aware Transformer for Large Hole Image Inpainting arXiv:2203.15270
Image GenerationonCelebA-HQ
FID· 2022-03-29
4.86
SOTA
MAT: Mask-Aware Transformer for Large Hole Image Inpainting arXiv:2203.15270
Image GenerationonCelebA-HQ
P-IDS· 2022-03-29
13.83
SOTA
MAT: Mask-Aware Transformer for Large Hole Image Inpainting arXiv:2203.15270
Image GenerationonCelebA-HQ
U-IDS· 2022-03-29
25.33
SOTA
MAT: Mask-Aware Transformer for Large Hole Image Inpainting arXiv:2203.15270
Image GenerationonPlaces2
FID· 2022-03-29
1.96
best: 1.23 (ASUKA)
MAT: Mask-Aware Transformer for Large Hole Image Inpainting arXiv:2203.15270
Medical Image SegmentationonSUN-SEG-Easy (Unseen)
Dice
0.71
best: 0.9 (YOLO-SAM 2)
Medical Image SegmentationonSUN-SEG-Easy (Unseen)
S measure
0.77
best: 0.9 (YOLO-SAM 2)
Medical Image SegmentationonSUN-SEG-Easy (Unseen)
Sensitivity
0.542
best: 83.7 (YOLO-SAM 2)
Medical Image SegmentationonSUN-SEG-Easy (Unseen)
mean E-measure
0.737
best: 93.8 (YOLO-SAM 2)
Medical Image SegmentationonSUN-SEG-Easy (Unseen)
mean F-measure
0.641
best: 93.8 (YOLO-SAM 2)
Medical Image SegmentationonSUN-SEG-Easy (Unseen)
weighted F-measure
0.575
best: 0.794 (SALI)
Medical Image SegmentationonSUN-SEG-Hard (Unseen)
Dice
0.712
best: 0.902 (YOLO-SAM 2)
Medical Image SegmentationonSUN-SEG-Hard (Unseen)
S-Measure
0.785
best: 0.894 (YOLO-SAM 2)
Medical Image SegmentationonSUN-SEG-Hard (Unseen)
Sensitivity
0.579
best: 0.852 (YOLO-SAM 2)
Medical Image SegmentationonSUN-SEG-Hard (Unseen)
mean E-measure
0.755
best: 0.941 (YOLO-SAM 2)
Medical Image SegmentationonSUN-SEG-Hard (Unseen)
mean F-measure
0.645
best: 0.932 (YOLO-SAM 2)
Medical Image SegmentationonSUN-SEG-Hard (Unseen)
weighted F-measure
0.578
best: 0.79 (SALI)

Computer Vision6 results

Image InpaintingonPlaces2
P-IDS· 2022-03-29
23.42
best: 28.7 (ASUKA)
SOTA
MAT: Mask-Aware Transformer for Large Hole Image Inpainting arXiv:2203.15270
Image InpaintingonPlaces2
U-IDS· 2022-03-29
38.34
best: 41.3 (ASUKA)
SOTA
MAT: Mask-Aware Transformer for Large Hole Image Inpainting arXiv:2203.15270
Image InpaintingonCelebA-HQ
FID· 2022-03-29
4.86
SOTA
MAT: Mask-Aware Transformer for Large Hole Image Inpainting arXiv:2203.15270
Image InpaintingonCelebA-HQ
P-IDS· 2022-03-29
13.83
SOTA
MAT: Mask-Aware Transformer for Large Hole Image Inpainting arXiv:2203.15270
Image InpaintingonCelebA-HQ
U-IDS· 2022-03-29
25.33
SOTA
MAT: Mask-Aware Transformer for Large Hole Image Inpainting arXiv:2203.15270
Image InpaintingonPlaces2
FID· 2022-03-29
1.96
best: 1.23 (ASUKA)
MAT: Mask-Aware Transformer for Large Hole Image Inpainting arXiv:2203.15270

Natural Language Processing2 results

Machine TranslationonIWSLT2014 German-English
BLEU score· 2020-06-18
36.22
best: 40.43 (PiNMT)
Multi-branch Attentive Transformer arXiv:2006.10270
Machine TranslationonWMT2014 English-German
SacreBLEU· 2020-06-18
29.9
best: 33.8 (Noisy back-translation)
Multi-branch Attentive Transformer arXiv:2006.10270