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/U-Net

U-Net

Reported on 107 benchmarks across 12 tasks · 10 papers · 64 SOTA

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

Medical78 results

Semantic SegmentationonDIVA-HisDB
Mean IoU (class)· 2022-01-20
97.26
SOTA
DIVA-DAF: A Deep Learning Framework for Historical Document Image Analysis arXiv:2201.08295
Medical Image SegmentationonDRIVE
Accuracy· 2021-05-19
0.9712
SOTA
Exploring The Limits Of Data Augmentation For Retinal Vessel Segmentation arXiv:2105.09365
Retinal Vessel SegmentationonDRIVE
Accuracy· 2021-05-19
0.9712
SOTA
Exploring The Limits Of Data Augmentation For Retinal Vessel Segmentation arXiv:2105.09365
Medical Image SegmentationonKvasir-SEG
S-Measure· 2015-05-18
0.858
best: 0.929 (CaraNet)
SOTA
U-Net: Convolutional Networks for Biomedical Image Segmentation arXiv:1505.04597
Medical Image SegmentationonKvasir-SEG
max E-Measure· 2015-05-18
0.893
best: 0.972 (BDG-Net)
SOTA
U-Net: Convolutional Networks for Biomedical Image Segmentation arXiv:1505.04597
Medical Image SegmentationonKvasir-SEG
mean Dice· 2015-05-18
0.818
best: 0.9502 (DUCK-Net)
SOTA
U-Net: Convolutional Networks for Biomedical Image Segmentation arXiv:1505.04597
Medical Image SegmentationonISBI 2012 EM Segmentation
Warping Error· 2015-05-18
0.000353
SOTA
U-Net: Convolutional Networks for Biomedical Image Segmentation arXiv:1505.04597
Medical Image SegmentationonCVC-ClinicDB
mean Dice· 2015-05-18
0.823
best: 0.9684 (DUCK-Net)
SOTA
U-Net: Convolutional Networks for Biomedical Image Segmentation arXiv:1505.04597
Medical Image SegmentationonRITE
Dice· 2015-05-18
55.24
best: 75.17 (KiU-Net)
SOTA
U-Net: Convolutional Networks for Biomedical Image Segmentation arXiv:1505.04597
Medical Image SegmentationonRITE
Jaccard Index· 2015-05-18
31.11
best: 60.37 (KiU-Net)
SOTA
U-Net: Convolutional Networks for Biomedical Image Segmentation arXiv:1505.04597
Medical Image SegmentationonAnatomical Tracings of Lesions After Stroke (ATLAS)
Dice· 2015-05-18
0.4606
best: 0.5349 (D-UNet)
SOTA
U-Net: Convolutional Networks for Biomedical Image Segmentation arXiv:1505.04597
Medical Image SegmentationonAnatomical Tracings of Lesions After Stroke (ATLAS)
IoU· 2015-05-18
0.3447
best: 0.3559 (2D Dense-UNet)
SOTA
U-Net: Convolutional Networks for Biomedical Image Segmentation arXiv:1505.04597
Medical Image SegmentationonAnatomical Tracings of Lesions After Stroke (ATLAS)
Precision· 2015-05-18
0.5994
best: 0.6331 (D-UNet)
SOTA
U-Net: Convolutional Networks for Biomedical Image Segmentation arXiv:1505.04597
Medical Image SegmentationonAnatomical Tracings of Lesions After Stroke (ATLAS)
Recall· 2015-05-18
0.4449
best: 0.5243 (D-UNet)
SOTA
U-Net: Convolutional Networks for Biomedical Image Segmentation arXiv:1505.04597
Medical Image SegmentationonBrain MRI segmentation
Dice Score· 2015-05-18
0.82
best: 0.8690000000000001 (SynthSeg)
SOTA
U-Net: Convolutional Networks for Biomedical Image Segmentation arXiv:1505.04597
Medical Image SegmentationonROSE-2
Dice Score· 2015-05-18
65.64
best: 71.18 (OCTAve: OCTA-Net)
SOTA
U-Net: Convolutional Networks for Biomedical Image Segmentation arXiv:1505.04597
Medical Image SegmentationonCHASE_DB1
AUC· 2015-05-18
0.9772
best: 0.9937 (FSG-Net)
SOTA
U-Net: Convolutional Networks for Biomedical Image Segmentation arXiv:1505.04597
Medical Image SegmentationonROSE-1 SVC-DVC
Dice Score· 2015-05-18
70.12
best: 81.42 (OCTAve: OCTA-Net)
SOTA
U-Net: Convolutional Networks for Biomedical Image Segmentation arXiv:1505.04597
Medical Image SegmentationonROSE-1 SVC
Dice Score· 2015-05-18
71.16
best: 78.03 (OCTAve: OCTA-Net)
SOTA
U-Net: Convolutional Networks for Biomedical Image Segmentation arXiv:1505.04597
Medical Image SegmentationonSTARE
AUC· 2015-05-18
0.7783
best: 0.9924 (DA-Net)
SOTA
U-Net: Convolutional Networks for Biomedical Image Segmentation arXiv:1505.04597
Medical Image SegmentationonSTARE
F1 score· 2015-05-18
0.8373
best: 0.8622 (DA-Net)
SOTA
U-Net: Convolutional Networks for Biomedical Image Segmentation arXiv:1505.04597
Medical Image SegmentationonROSE-1 DVC
Dice Score· 2015-05-18
66.05
best: 70.74 (OCTA-Net)
SOTA
U-Net: Convolutional Networks for Biomedical Image Segmentation arXiv:1505.04597
Medical Image SegmentationonDRIVE
AUC· 2015-05-18
0.9755
best: 0.9931 (Swin-Res-Net)
SOTA
U-Net: Convolutional Networks for Biomedical Image Segmentation arXiv:1505.04597
Medical Image SegmentationonDRIVE
F1 score· 2015-05-18
0.8142
best: 0.8322 (FSG-Net)
SOTA
U-Net: Convolutional Networks for Biomedical Image Segmentation arXiv:1505.04597
Medical Image SegmentationonCT-150
Dice Score· 2015-05-18
0.814
SOTA
U-Net: Convolutional Networks for Biomedical Image Segmentation arXiv:1505.04597
Medical Image SegmentationonCT-150
Precision· 2015-05-18
0.848
best: 0.849 (Att U-Net)
SOTA
U-Net: Convolutional Networks for Biomedical Image Segmentation arXiv:1505.04597
Medical Image SegmentationonCT-150
Recall· 2015-05-18
0.806
best: 0.841 (Att U-Net)
SOTA
U-Net: Convolutional Networks for Biomedical Image Segmentation arXiv:1505.04597
Medical Image SegmentationonTCIA Pancreas-CT Dataset
Dice Score· 2015-05-18
0.82
best: 0.845 (Recurrent Saliency Transformation Network)
SOTA
U-Net: Convolutional Networks for Biomedical Image Segmentation arXiv:1505.04597
Medical Image SegmentationonLUNA
AUC· 2015-05-18
0.9784
best: 0.9946 (BCDU-Net (d=3))
SOTA
U-Net: Convolutional Networks for Biomedical Image Segmentation arXiv:1505.04597
Medical Image SegmentationonLUNA
F1 score· 2015-05-18
0.9658
best: 0.9904 (BCDU-Net (d=3))
SOTA
U-Net: Convolutional Networks for Biomedical Image Segmentation arXiv:1505.04597
Medical Image SegmentationonKaggle Skin Lesion Segmentation
AUC· 2015-05-18
0.9371
best: 0.9419 (R2U-Net)
SOTA
U-Net: Convolutional Networks for Biomedical Image Segmentation arXiv:1505.04597
Medical Image SegmentationonKaggle Skin Lesion Segmentation
F1 score· 2015-05-18
0.8682
best: 0.892 (R2U-Net)
SOTA
U-Net: Convolutional Networks for Biomedical Image Segmentation arXiv:1505.04597
Medical Image SegmentationonSNEMI3D
AUC· 2015-05-18
0.8676
best: 0.8953 (DTN)
SOTA
U-Net: Convolutional Networks for Biomedical Image Segmentation arXiv:1505.04597
Semantic SegmentationonEvent-based Segmentation Dataset
mIoU· 2015-05-18
64.7
best: 87.05 (Bimodal SegNet)
SOTA
U-Net: Convolutional Networks for Biomedical Image Segmentation arXiv:1505.04597
Semantic SegmentationonTrans10K
GFLOPs· 2015-05-18
124.55
best: 198 (DANet)
SOTA
U-Net: Convolutional Networks for Biomedical Image Segmentation arXiv:1505.04597
Colorectal Gland Segmentation:onSTARE
AUC· 2015-05-18
0.835
SOTA
U-Net: Convolutional Networks for Biomedical Image Segmentation arXiv:1505.04597
3D Medical Imaging SegmentationonCT-150
Dice Score· 2015-05-18
0.814
SOTA
U-Net: Convolutional Networks for Biomedical Image Segmentation arXiv:1505.04597
3D Medical Imaging SegmentationonCT-150
Precision· 2015-05-18
0.848
best: 0.849 (Att U-Net)
SOTA
U-Net: Convolutional Networks for Biomedical Image Segmentation arXiv:1505.04597
3D Medical Imaging SegmentationonCT-150
Recall· 2015-05-18
0.806
best: 0.841 (Att U-Net)
SOTA
U-Net: Convolutional Networks for Biomedical Image Segmentation arXiv:1505.04597
3D Medical Imaging SegmentationonTCIA Pancreas-CT Dataset
Dice Score· 2015-05-18
0.82
best: 0.845 (Recurrent Saliency Transformation Network)
SOTA
U-Net: Convolutional Networks for Biomedical Image Segmentation arXiv:1505.04597
Retinal Vessel SegmentationonROSE-2
Dice Score· 2015-05-18
65.64
best: 71.18 (OCTAve: OCTA-Net)
SOTA
U-Net: Convolutional Networks for Biomedical Image Segmentation arXiv:1505.04597
Retinal Vessel SegmentationonCHASE_DB1
AUC· 2015-05-18
0.9772
best: 0.9937 (FSG-Net)
SOTA
U-Net: Convolutional Networks for Biomedical Image Segmentation arXiv:1505.04597
Retinal Vessel SegmentationonROSE-1 SVC-DVC
Dice Score· 2015-05-18
70.12
best: 81.42 (OCTAve: OCTA-Net)
SOTA
U-Net: Convolutional Networks for Biomedical Image Segmentation arXiv:1505.04597
Retinal Vessel SegmentationonROSE-1 SVC
Dice Score· 2015-05-18
71.16
best: 78.03 (OCTAve: OCTA-Net)
SOTA
U-Net: Convolutional Networks for Biomedical Image Segmentation arXiv:1505.04597
Retinal Vessel SegmentationonSTARE
AUC· 2015-05-18
0.7783
best: 0.9924 (DA-Net)
SOTA
U-Net: Convolutional Networks for Biomedical Image Segmentation arXiv:1505.04597
Retinal Vessel SegmentationonSTARE
F1 score· 2015-05-18
0.8373
best: 0.8622 (DA-Net)
SOTA
U-Net: Convolutional Networks for Biomedical Image Segmentation arXiv:1505.04597
Retinal Vessel SegmentationonROSE-1 DVC
Dice Score· 2015-05-18
66.05
best: 70.74 (OCTA-Net)
SOTA
U-Net: Convolutional Networks for Biomedical Image Segmentation arXiv:1505.04597
Retinal Vessel SegmentationonDRIVE
AUC· 2015-05-18
0.9755
best: 0.9931 (Swin-Res-Net)
SOTA
U-Net: Convolutional Networks for Biomedical Image Segmentation arXiv:1505.04597
Retinal Vessel SegmentationonDRIVE
F1 score· 2015-05-18
0.8142
best: 0.8322 (FSG-Net)
SOTA
U-Net: Convolutional Networks for Biomedical Image Segmentation arXiv:1505.04597
Semantic SegmentationonHyperspectral City
Accuracy · 2024-09-17
85.25
best: 87.63 (RU-Net)
HS3-Bench: A Benchmark and Strong Baseline for Hyperspectral Semantic Segmentation in Driving Scenarios arXiv:2409.11205
Semantic SegmentationonHyperspectral City
Average Accuracy· 2024-09-17
48.62
best: 54.14 (RU-Net)
HS3-Bench: A Benchmark and Strong Baseline for Hyperspectral Semantic Segmentation in Driving Scenarios arXiv:2409.11205
Semantic SegmentationonHyperspectral City
Avg. F1· 2024-09-17
48.18
best: 53.26 (RU-Net)
HS3-Bench: A Benchmark and Strong Baseline for Hyperspectral Semantic Segmentation in Driving Scenarios arXiv:2409.11205
Semantic SegmentationonHyperspectral City
Jaccard (Mean)· 2024-09-17
37.73
best: 43.33 (RU-Net)
HS3-Bench: A Benchmark and Strong Baseline for Hyperspectral Semantic Segmentation in Driving Scenarios arXiv:2409.11205
Semantic SegmentationonHSI-Drive v2.0
Accuracy· 2024-09-17
94.95
best: 96.08 (RU-Net)
HS3-Bench: A Benchmark and Strong Baseline for Hyperspectral Semantic Segmentation in Driving Scenarios arXiv:2409.11205
Semantic SegmentationonHSI-Drive v2.0
Average Accuracy· 2024-09-17
74.74
best: 79.82 (RU-Net)
HS3-Bench: A Benchmark and Strong Baseline for Hyperspectral Semantic Segmentation in Driving Scenarios arXiv:2409.11205
Semantic SegmentationonHSI-Drive v2.0
Avg. F1· 2024-09-17
76.08
best: 82.34 (RU-Net)
HS3-Bench: A Benchmark and Strong Baseline for Hyperspectral Semantic Segmentation in Driving Scenarios arXiv:2409.11205
Semantic SegmentationonHSI-Drive v2.0
Jaccard (Mean)· 2024-09-17
64.95
best: 72.18 (RU-Net)
HS3-Bench: A Benchmark and Strong Baseline for Hyperspectral Semantic Segmentation in Driving Scenarios arXiv:2409.11205
Semantic SegmentationonHyKo2-VIS
Accuracy· 2024-09-17
85.36
best: 86.72 (RU-Net)
HS3-Bench: A Benchmark and Strong Baseline for Hyperspectral Semantic Segmentation in Driving Scenarios arXiv:2409.11205
Semantic SegmentationonHyKo2-VIS
Average Accuracy· 2024-09-17
68.15
best: 68.79 (RU-Net)
HS3-Bench: A Benchmark and Strong Baseline for Hyperspectral Semantic Segmentation in Driving Scenarios arXiv:2409.11205
Semantic SegmentationonHyKo2-VIS
Average Jaccard· 2024-09-17
57.39
best: 58.64 (RU-Net)
HS3-Bench: A Benchmark and Strong Baseline for Hyperspectral Semantic Segmentation in Driving Scenarios arXiv:2409.11205
Semantic SegmentationonHyKo2-VIS
Avg. F1· 2024-09-17
68.55
best: 69.19 (RU-Net)
HS3-Bench: A Benchmark and Strong Baseline for Hyperspectral Semantic Segmentation in Driving Scenarios arXiv:2409.11205
Semantic SegmentationonFLAIR (French Land cover from Aerospace ImageRy)
mIoU· 2023-10-20
54.7
best: 64.1 (Ensemble-04 MiT-0 MiT-1 RNX-1 RNX-2)
FLAIR: a Country-Scale Land Cover Semantic Segmentation Dataset From Multi-Source Optical Imagery arXiv:2310.13336
Medical Image SegmentationonKvasir-SEG
Average MAE· 2022-10-12
0.055
best: 0.021 (BDG-Net)
Flare7K: A Phenomenological Nighttime Flare Removal Dataset arXiv:2210.06570
Medical Image SegmentationonGlaS
Dice· 2021-09-09
85.45
best: 93.25 (Hi-gMISnet)
UCTransNet: Rethinking the Skip Connections in U-Net from a Channel-wise Perspective with Transformer arXiv:2109.04335
Medical Image SegmentationonGlaS
F1· 2021-09-09
85.45
best: 93.25 (Hi-gMISnet)
UCTransNet: Rethinking the Skip Connections in U-Net from a Channel-wise Perspective with Transformer arXiv:2109.04335
Medical Image SegmentationonGlaS
IoU· 2021-09-09
74.78
best: 85.13 (MDM)
UCTransNet: Rethinking the Skip Connections in U-Net from a Channel-wise Perspective with Transformer arXiv:2109.04335
Medical Image SegmentationonDRIVE
AUC· 2021-05-19
0.9855
best: 0.9931 (Swin-Res-Net)
Exploring The Limits Of Data Augmentation For Retinal Vessel Segmentation arXiv:2105.09365
Retinal Vessel SegmentationonDRIVE
AUC· 2021-05-19
0.9855
best: 0.9931 (Swin-Res-Net)
Exploring The Limits Of Data Augmentation For Retinal Vessel Segmentation arXiv:2105.09365
Medical Image SegmentationonBrain US
F1· 2021-02-21
87.92
best: 88.84 (MedT)
Medical Transformer: Gated Axial-Attention for Medical Image Segmentation arXiv:2102.10662
Medical Image SegmentationonBrain US
IoU· 2021-02-21
80.14
best: 81.34 (MedT)
Medical Transformer: Gated Axial-Attention for Medical Image Segmentation arXiv:2102.10662
Medical Image SegmentationonGlaS
Dice· 2021-02-21
76.26
best: 93.25 (Hi-gMISnet)
Medical Transformer: Gated Axial-Attention for Medical Image Segmentation arXiv:2102.10662
Medical Image SegmentationonGlaS
F1· 2021-02-21
76.26
best: 93.25 (Hi-gMISnet)
Medical Transformer: Gated Axial-Attention for Medical Image Segmentation arXiv:2102.10662
Medical Image SegmentationonGlaS
IoU· 2021-02-21
63.03
best: 85.13 (MDM)
Medical Transformer: Gated Axial-Attention for Medical Image Segmentation arXiv:2102.10662
Medical Image SegmentationonMoNuSeg
F1· 2021-02-21
76.83
best: 84.6 (Stardist)
Medical Transformer: Gated Axial-Attention for Medical Image Segmentation arXiv:2102.10662
Medical Image SegmentationonMoNuSeg
IoU· 2021-02-21
62.49
best: 73.06 (ReN-UNet)
Medical Transformer: Gated Axial-Attention for Medical Image Segmentation arXiv:2102.10662
Medical Image SegmentationonSTARE
AUC· 2015-05-18
0.7756
best: 0.9924 (DA-Net)
U-Net: Convolutional Networks for Biomedical Image Segmentation arXiv:1505.04597
Semantic SegmentationonSkyScapes-Dense
Mean IoU· 2015-05-18
14.15
best: 40.13 (SkyScapesNet-Dense)
U-Net: Convolutional Networks for Biomedical Image Segmentation arXiv:1505.04597
Sleep QualityonMESA
event-based F1 score
0.81

Audio29 results

10-shot image generationonFlare7K
LPIPS· 2022-10-12
0.055
best: 0.0422 (Kotp et al)
SOTA
Flare7K: A Phenomenological Nighttime Flare Removal Dataset arXiv:2210.06570
10-shot image generationonDIVA-HisDB
Mean IoU (class)· 2022-01-20
97.26
SOTA
DIVA-DAF: A Deep Learning Framework for Historical Document Image Analysis arXiv:2201.08295
Audio GenerationonPiano
Log-Spectral Distance· 2017-08-02
3.4
SOTA
Audio Super Resolution using Neural Networks arXiv:1708.00853
Audio GenerationonVCTK Multi-Speaker
Log-Spectral Distance· 2017-08-02
3.1
SOTA
Audio Super Resolution using Neural Networks arXiv:1708.00853
Audio GenerationonVoice Bank corpus (VCTK)
Log-Spectral Distance· uses extra data· 2017-08-02
3.2
SOTA
Audio Super Resolution using Neural Networks arXiv:1708.00853
10-shot image generationonPiano
Log-Spectral Distance· 2017-08-02
3.4
SOTA
Audio Super Resolution using Neural Networks arXiv:1708.00853
10-shot image generationonVCTK Multi-Speaker
Log-Spectral Distance· 2017-08-02
3.1
SOTA
Audio Super Resolution using Neural Networks arXiv:1708.00853
10-shot image generationonVoice Bank corpus (VCTK)
Log-Spectral Distance· uses extra data· 2017-08-02
3.2
SOTA
Audio Super Resolution using Neural Networks arXiv:1708.00853
Audio Super-ResolutiononPiano
Log-Spectral Distance· 2017-08-02
3.4
SOTA
Audio Super Resolution using Neural Networks arXiv:1708.00853
Audio Super-ResolutiononVCTK Multi-Speaker
Log-Spectral Distance· 2017-08-02
3.1
SOTA
Audio Super Resolution using Neural Networks arXiv:1708.00853
Audio Super-ResolutiononVoice Bank corpus (VCTK)
Log-Spectral Distance· uses extra data· 2017-08-02
3.2
SOTA
Audio Super Resolution using Neural Networks arXiv:1708.00853
10-shot image generationonEvent-based Segmentation Dataset
mIoU· 2015-05-18
64.7
best: 87.05 (Bimodal SegNet)
SOTA
U-Net: Convolutional Networks for Biomedical Image Segmentation arXiv:1505.04597
10-shot image generationonTrans10K
GFLOPs· 2015-05-18
124.55
best: 198 (DANet)
SOTA
U-Net: Convolutional Networks for Biomedical Image Segmentation arXiv:1505.04597
10-shot image generationonHyperspectral City
Accuracy · 2024-09-17
85.25
best: 87.63 (RU-Net)
HS3-Bench: A Benchmark and Strong Baseline for Hyperspectral Semantic Segmentation in Driving Scenarios arXiv:2409.11205
10-shot image generationonHyperspectral City
Average Accuracy· 2024-09-17
48.62
best: 54.14 (RU-Net)
HS3-Bench: A Benchmark and Strong Baseline for Hyperspectral Semantic Segmentation in Driving Scenarios arXiv:2409.11205
10-shot image generationonHyperspectral City
Avg. F1· 2024-09-17
48.18
best: 53.26 (RU-Net)
HS3-Bench: A Benchmark and Strong Baseline for Hyperspectral Semantic Segmentation in Driving Scenarios arXiv:2409.11205
10-shot image generationonHyperspectral City
Jaccard (Mean)· 2024-09-17
37.73
best: 43.33 (RU-Net)
HS3-Bench: A Benchmark and Strong Baseline for Hyperspectral Semantic Segmentation in Driving Scenarios arXiv:2409.11205
10-shot image generationonHSI-Drive v2.0
Accuracy· 2024-09-17
94.95
best: 96.08 (RU-Net)
HS3-Bench: A Benchmark and Strong Baseline for Hyperspectral Semantic Segmentation in Driving Scenarios arXiv:2409.11205
10-shot image generationonHSI-Drive v2.0
Average Accuracy· 2024-09-17
74.74
best: 79.82 (RU-Net)
HS3-Bench: A Benchmark and Strong Baseline for Hyperspectral Semantic Segmentation in Driving Scenarios arXiv:2409.11205
10-shot image generationonHSI-Drive v2.0
Avg. F1· 2024-09-17
76.08
best: 82.34 (RU-Net)
HS3-Bench: A Benchmark and Strong Baseline for Hyperspectral Semantic Segmentation in Driving Scenarios arXiv:2409.11205
10-shot image generationonHSI-Drive v2.0
Jaccard (Mean)· 2024-09-17
64.95
best: 72.18 (RU-Net)
HS3-Bench: A Benchmark and Strong Baseline for Hyperspectral Semantic Segmentation in Driving Scenarios arXiv:2409.11205
10-shot image generationonHyKo2-VIS
Accuracy· 2024-09-17
85.36
best: 86.72 (RU-Net)
HS3-Bench: A Benchmark and Strong Baseline for Hyperspectral Semantic Segmentation in Driving Scenarios arXiv:2409.11205
10-shot image generationonHyKo2-VIS
Average Accuracy· 2024-09-17
68.15
best: 68.79 (RU-Net)
HS3-Bench: A Benchmark and Strong Baseline for Hyperspectral Semantic Segmentation in Driving Scenarios arXiv:2409.11205
10-shot image generationonHyKo2-VIS
Average Jaccard· 2024-09-17
57.39
best: 58.64 (RU-Net)
HS3-Bench: A Benchmark and Strong Baseline for Hyperspectral Semantic Segmentation in Driving Scenarios arXiv:2409.11205
10-shot image generationonHyKo2-VIS
Avg. F1· 2024-09-17
68.55
best: 69.19 (RU-Net)
HS3-Bench: A Benchmark and Strong Baseline for Hyperspectral Semantic Segmentation in Driving Scenarios arXiv:2409.11205
10-shot image generationonFLAIR (French Land cover from Aerospace ImageRy)
mIoU· 2023-10-20
54.7
best: 64.1 (Ensemble-04 MiT-0 MiT-1 RNX-1 RNX-2)
FLAIR: a Country-Scale Land Cover Semantic Segmentation Dataset From Multi-Source Optical Imagery arXiv:2310.13336
10-shot image generationonFlare7K
PSNR· 2022-10-12
26.11
best: 27.662 (Kotp et al)
Flare7K: A Phenomenological Nighttime Flare Removal Dataset arXiv:2210.06570
10-shot image generationonFlare7K
SSIM· 2022-10-12
0.879
best: 0.901 (FF-Former)
Flare7K: A Phenomenological Nighttime Flare Removal Dataset arXiv:2210.06570
10-shot image generationonSkyScapes-Dense
Mean IoU· 2015-05-18
14.15
best: 40.13 (SkyScapesNet-Dense)
U-Net: Convolutional Networks for Biomedical Image Segmentation arXiv:1505.04597

Computer Vision4 results

Image RestorationonFlare7K
LPIPS· 2022-10-12
0.055
best: 0.0422 (Kotp et al)
SOTA
Flare7K: A Phenomenological Nighttime Flare Removal Dataset arXiv:2210.06570
Cell SegmentationonSTARE
AUC· 2015-05-18
0.7756
SOTA
U-Net: Convolutional Networks for Biomedical Image Segmentation arXiv:1505.04597
Image RestorationonFlare7K
PSNR· 2022-10-12
26.11
best: 27.662 (Kotp et al)
Flare7K: A Phenomenological Nighttime Flare Removal Dataset arXiv:2210.06570
Image RestorationonFlare7K
SSIM· 2022-10-12
0.879
best: 0.901 (FF-Former)
Flare7K: A Phenomenological Nighttime Flare Removal Dataset arXiv:2210.06570

Natural Language Processing2 results

Question AnsweringonSQuAD2.0 dev
EM· 2018-10-12
70.3
best: 87.9 (XLNet (single model))
U-Net: Machine Reading Comprehension with Unanswerable Questions arXiv:1810.06638
Question AnsweringonSQuAD2.0 dev
F1· 2018-10-12
74
best: 90.6 (XLNet (single model))
U-Net: Machine Reading Comprehension with Unanswerable Questions arXiv:1810.06638