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/DeepLabV3+

DeepLabV3+

Reported on 36 benchmarks across 4 tasks · 4 papers · 7 SOTA

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

Audio18 results

10-shot image generationonUS3D
mIoU· 2018-02-07
74.42
SOTA
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation arXiv:1802.02611
10-shot image generationonPotsdam
mIoU· 2018-02-07
83.67
best: 84.22 (HRNet-48)
SOTA
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation arXiv:1802.02611
10-shot image generationonEventScape
mIoU· 2018-02-07
53.65
best: 64.28 (CMX (B4))
SOTA
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation arXiv:1802.02611
2D Semantic SegmentationonBRIGHT
mIOU· 2025-01-10
64.8
best: 67.63 (ChangeMamba)
BRIGHT: A globally distributed multimodal building damage assessment dataset with very-high-resolution for all-weather disaster response arXiv:2501.06019
10-shot image generationonHyperspectral City
Accuracy · 2024-09-17
86.6
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
53.15
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
51.83
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
40.79
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
92.51
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
65.58
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
67.86
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
56.63
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
84.1
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
63.01
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
53.22
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
64.9
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 generationonVaihingen
mIoU· 2018-02-07
72.9
best: 82.87 (CMX)
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation arXiv:1802.02611
10-shot image generationonTrans10K
GFLOPs· 2018-02-07
37.98
best: 198 (DANet)
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation arXiv:1802.02611

Medical17 results

Semantic SegmentationonUS3D
mIoU· 2018-02-07
74.42
SOTA
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation arXiv:1802.02611
Semantic SegmentationonPotsdam
mIoU· 2018-02-07
83.67
best: 84.22 (HRNet-48)
SOTA
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation arXiv:1802.02611
Semantic SegmentationonEventScape
mIoU· 2018-02-07
53.65
best: 64.28 (CMX (B4))
SOTA
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation arXiv:1802.02611
Semantic SegmentationonHyperspectral City
Accuracy · 2024-09-17
86.6
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
53.15
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
51.83
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
40.79
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
92.51
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
65.58
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
67.86
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
56.63
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
84.1
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
63.01
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
53.22
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
64.9
best: 69.19 (RU-Net)
HS3-Bench: A Benchmark and Strong Baseline for Hyperspectral Semantic Segmentation in Driving Scenarios arXiv:2409.11205
Semantic SegmentationonVaihingen
mIoU· 2018-02-07
72.9
best: 82.87 (CMX)
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation arXiv:1802.02611
Semantic SegmentationonTrans10K
GFLOPs· 2018-02-07
37.98
best: 198 (DANet)
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation arXiv:1802.02611

Computer Vision1 result

Document Layout AnalysisonU-DIADS-Bib
Class Average IoU· 2024-01-16
66.5
best: 83.4 (CV-Group)
SOTA
U-DIADS-Bib: a full and few-shot pixel-precise dataset for document layout analysis of ancient manuscripts arXiv:2401.08425