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/SST

SST

Reported on 45 benchmarks across 10 tasks · 4 papers · 21 SOTA

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

Computer Vision30 results

Multi-Label Image ClassificationonMS-COCO-2014
Average mAP· 2021-12-21
76.7
best: 83.6 (DualCoOp+TaI-DPT)
SOTA
Structured Semantic Transfer for Multi-Label Recognition with Partial Labels arXiv:2112.10941
Multi-Label Image ClassificationonPASCAL VOC 2007
Average mAP· 2021-12-21
90.4
best: 94.8 (DualCoOp+TaI-DPT)
SOTA
Structured Semantic Transfer for Multi-Label Recognition with Partial Labels arXiv:2112.10941
Multi-Label Image ClassificationonVisual Genome
Average mAP· 2021-12-21
41.8
best: 46 (DSRB)
SOTA
Structured Semantic Transfer for Multi-Label Recognition with Partial Labels arXiv:2112.10941
Image ClassificationonMS-COCO-2014
Average mAP· 2021-12-21
76.7
best: 83.6 (DualCoOp+TaI-DPT)
SOTA
Structured Semantic Transfer for Multi-Label Recognition with Partial Labels arXiv:2112.10941
Image ClassificationonPASCAL VOC 2007
Average mAP· 2021-12-21
90.4
best: 94.8 (DualCoOp+TaI-DPT)
SOTA
Structured Semantic Transfer for Multi-Label Recognition with Partial Labels arXiv:2112.10941
Image ClassificationonVisual Genome
Average mAP· 2021-12-21
41.8
best: 46 (DSRB)
SOTA
Structured Semantic Transfer for Multi-Label Recognition with Partial Labels arXiv:2112.10941
Object Detectiononwaymo cyclist
APH/L2· 2021-12-13
72.17
best: 78 (DSVT(val))
SOTA
Embracing Single Stride 3D Object Detector with Sparse Transformer arXiv:2112.06375
Object Detectiononwaymo pedestrian
APH/L2· 2021-12-13
73.51
best: 76.4 (DSVT(val))
SOTA
Embracing Single Stride 3D Object Detector with Sparse Transformer arXiv:2112.06375
3D Object Detectiononwaymo cyclist
APH/L2· 2021-12-13
72.17
best: 78 (DSVT(val))
SOTA
Embracing Single Stride 3D Object Detector with Sparse Transformer arXiv:2112.06375
3D Object Detectiononwaymo pedestrian
APH/L2· 2021-12-13
73.51
best: 76.4 (DSVT(val))
SOTA
Embracing Single Stride 3D Object Detector with Sparse Transformer arXiv:2112.06375
VideoonYouTube-VOS 2018
Jaccard (Seen)· 2022-08-01
81.2
best: 86.6 (Cutie+ (base, MEGA))
BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation arXiv:2208.01159
VideoonYouTube-VOS 2018
Jaccard (Unseen)· 2022-08-01
76
best: 82.2 (Cutie+ (base, MEGA))
BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation arXiv:2208.01159
VideoonYouTube-VOS 2018
Mean Jaccard & F-Measure· 2022-08-01
81.7
best: 86.9 (XMem (BL30K, MS))
BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation arXiv:2208.01159
VideoonDAVIS 2017 (val)
F-measure· 2022-08-01
85.1
best: 92.6 (XMem (BLK30K, MS))
BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation arXiv:2208.01159
VideoonDAVIS 2017 (val)
Jaccard· 2022-08-01
79.9
best: 86.3 (XMem (BLK30K, MS))
BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation arXiv:2208.01159
VideoonDAVIS 2017 (val)
Mean Jaccard & F-Measure· 2022-08-01
82.5
best: 89.5 (XMem (BLK30K, MS))
BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation arXiv:2208.01159
Video Object SegmentationonYouTube-VOS 2018
Jaccard (Seen)· 2022-08-01
81.2
best: 86.6 (Cutie+ (base, MEGA))
BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation arXiv:2208.01159
Video Object SegmentationonYouTube-VOS 2018
Jaccard (Unseen)· 2022-08-01
76
best: 82.2 (Cutie+ (base, MEGA))
BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation arXiv:2208.01159
Video Object SegmentationonYouTube-VOS 2018
Mean Jaccard & F-Measure· 2022-08-01
81.7
best: 86.9 (XMem (BL30K, MS))
BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation arXiv:2208.01159
Video Object SegmentationonDAVIS 2017 (val)
F-measure· 2022-08-01
85.1
best: 92.6 (XMem (BLK30K, MS))
BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation arXiv:2208.01159
Video Object SegmentationonDAVIS 2017 (val)
Jaccard· 2022-08-01
79.9
best: 86.3 (XMem (BLK30K, MS))
BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation arXiv:2208.01159
Video Object SegmentationonDAVIS 2017 (val)
Mean Jaccard & F-Measure· 2022-08-01
82.5
best: 89.5 (XMem (BLK30K, MS))
BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation arXiv:2208.01159
Object Detectiononwaymo vehicle
APH/L2· 2021-12-13
72.74
best: 75.76 (PillarNeXt)
Embracing Single Stride 3D Object Detector with Sparse Transformer arXiv:2112.06375
3D Object Detectiononwaymo vehicle
APH/L2· 2021-12-13
72.74
best: 75.76 (PillarNeXt)
Embracing Single Stride 3D Object Detector with Sparse Transformer arXiv:2112.06375
VideoonYouTube-VOS 2019
Jaccard (Seen)· 2021-01-21
80.9
best: 86.3 (Cutie+ (base, MEGA))
SSTVOS: Sparse Spatiotemporal Transformers for Video Object Segmentation arXiv:2101.08833
VideoonYouTube-VOS 2019
Jaccard (Unseen)· 2021-01-21
76.6
best: 754.8 (R50-AOST (L'=1))
SSTVOS: Sparse Spatiotemporal Transformers for Video Object Segmentation arXiv:2101.08833
VideoonYouTube-VOS 2019
Mean Jaccard & F-Measure· 2021-01-21
81.8
best: 86.8 (XMem (BL30K,MS))
SSTVOS: Sparse Spatiotemporal Transformers for Video Object Segmentation arXiv:2101.08833
Video Object SegmentationonYouTube-VOS 2019
Jaccard (Seen)· 2021-01-21
80.9
best: 86.3 (Cutie+ (base, MEGA))
SSTVOS: Sparse Spatiotemporal Transformers for Video Object Segmentation arXiv:2101.08833
Video Object SegmentationonYouTube-VOS 2019
Jaccard (Unseen)· 2021-01-21
76.6
best: 754.8 (R50-AOST (L'=1))
SSTVOS: Sparse Spatiotemporal Transformers for Video Object Segmentation arXiv:2101.08833
Video Object SegmentationonYouTube-VOS 2019
Mean Jaccard & F-Measure· 2021-01-21
81.8
best: 86.8 (XMem (BL30K,MS))
SSTVOS: Sparse Spatiotemporal Transformers for Video Object Segmentation arXiv:2101.08833

Methodology15 results

2D ClassificationonMS-COCO-2014
Average mAP· 2021-12-21
76.7
best: 83.6 (DualCoOp+TaI-DPT)
SOTA
Structured Semantic Transfer for Multi-Label Recognition with Partial Labels arXiv:2112.10941
2D ClassificationonPASCAL VOC 2007
Average mAP· 2021-12-21
90.4
best: 94.8 (DualCoOp+TaI-DPT)
SOTA
Structured Semantic Transfer for Multi-Label Recognition with Partial Labels arXiv:2112.10941
2D ClassificationonVisual Genome
Average mAP· 2021-12-21
41.8
best: 46 (DSRB)
SOTA
Structured Semantic Transfer for Multi-Label Recognition with Partial Labels arXiv:2112.10941
3Donwaymo cyclist
APH/L2· 2021-12-13
72.17
best: 78 (DSVT(val))
SOTA
Embracing Single Stride 3D Object Detector with Sparse Transformer arXiv:2112.06375
3Donwaymo pedestrian
APH/L2· 2021-12-13
73.51
best: 76.4 (DSVT(val))
SOTA
Embracing Single Stride 3D Object Detector with Sparse Transformer arXiv:2112.06375
2D Classificationonwaymo cyclist
APH/L2· 2021-12-13
72.17
best: 78 (DSVT(val))
SOTA
Embracing Single Stride 3D Object Detector with Sparse Transformer arXiv:2112.06375
2D Classificationonwaymo pedestrian
APH/L2· 2021-12-13
73.51
best: 76.4 (DSVT(val))
SOTA
Embracing Single Stride 3D Object Detector with Sparse Transformer arXiv:2112.06375
2D Object Detectiononwaymo cyclist
APH/L2· 2021-12-13
72.17
best: 78 (DSVT(val))
SOTA
Embracing Single Stride 3D Object Detector with Sparse Transformer arXiv:2112.06375
2D Object Detectiononwaymo pedestrian
APH/L2· 2021-12-13
73.51
best: 76.4 (DSVT(val))
SOTA
Embracing Single Stride 3D Object Detector with Sparse Transformer arXiv:2112.06375
16konwaymo cyclist
APH/L2· 2021-12-13
72.17
best: 78 (DSVT(val))
SOTA
Embracing Single Stride 3D Object Detector with Sparse Transformer arXiv:2112.06375
16konwaymo pedestrian
APH/L2· 2021-12-13
73.51
best: 76.4 (DSVT(val))
SOTA
Embracing Single Stride 3D Object Detector with Sparse Transformer arXiv:2112.06375
3Donwaymo vehicle
APH/L2· 2021-12-13
72.74
best: 75.76 (PillarNeXt)
Embracing Single Stride 3D Object Detector with Sparse Transformer arXiv:2112.06375
2D Classificationonwaymo vehicle
APH/L2· 2021-12-13
72.74
best: 75.76 (PillarNeXt)
Embracing Single Stride 3D Object Detector with Sparse Transformer arXiv:2112.06375
2D Object Detectiononwaymo vehicle
APH/L2· 2021-12-13
72.74
best: 75.76 (PillarNeXt)
Embracing Single Stride 3D Object Detector with Sparse Transformer arXiv:2112.06375
16konwaymo vehicle
APH/L2· 2021-12-13
72.74
best: 75.76 (PillarNeXt)
Embracing Single Stride 3D Object Detector with Sparse Transformer arXiv:2112.06375