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/LCM

LCM

Reported on 38 benchmarks across 7 tasks · 3 papers · 4 SOTA

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

Computer Vision26 results

VideoonDAVIS 2017 (test-dev)
F-measure· 2022-08-01
81.8
best: 86.1 (BATMAN)
BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation arXiv:2208.01159
VideoonDAVIS 2017 (test-dev)
Jaccard· 2022-08-01
74.4
best: 78.4 (BATMAN)
BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation arXiv:2208.01159
VideoonDAVIS 2017 (test-dev)
Mean Jaccard & F-Measure· 2022-08-01
78.1
best: 82.2 (BATMAN)
BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation arXiv:2208.01159
VideoonYouTube-VOS 2018
Jaccard (Seen)· 2022-08-01
82.2
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
Mean Jaccard & F-Measure· 2022-08-01
82
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
86.5
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
80.5
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 (test-dev)
F-measure· 2022-08-01
81.8
best: 86.1 (BATMAN)
BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation arXiv:2208.01159
Video Object SegmentationonDAVIS 2017 (test-dev)
Jaccard· 2022-08-01
74.4
best: 78.4 (BATMAN)
BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation arXiv:2208.01159
Video Object SegmentationonDAVIS 2017 (test-dev)
Mean Jaccard & F-Measure· 2022-08-01
78.1
best: 82.2 (BATMAN)
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
82.2
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
Mean Jaccard & F-Measure· 2022-08-01
82
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
86.5
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
80.5
best: 86.3 (XMem (BLK30K, MS))
BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation arXiv:2208.01159
VideoonDAVIS (no YouTube-VOS training)
D17 val (F)· 2021-04-09
77.2
best: 83.1 (HMMN)
Learning Position and Target Consistency for Memory-based Video Object Segmentation arXiv:2104.04329
VideoonDAVIS (no YouTube-VOS training)
D17 val (G)· 2021-04-09
75.2
best: 80.4 (HMMN)
Learning Position and Target Consistency for Memory-based Video Object Segmentation arXiv:2104.04329
VideoonDAVIS (no YouTube-VOS training)
D17 val (J)· 2021-04-09
73.1
best: 77.7 (HMMN)
Learning Position and Target Consistency for Memory-based Video Object Segmentation arXiv:2104.04329
VideoonDAVIS (no YouTube-VOS training)
FPS· 2021-04-09
8.47
best: 50.1 (TBD)
Learning Position and Target Consistency for Memory-based Video Object Segmentation arXiv:2104.04329
Video Object SegmentationonDAVIS (no YouTube-VOS training)
D17 val (F)· 2021-04-09
77.2
best: 83.1 (HMMN)
Learning Position and Target Consistency for Memory-based Video Object Segmentation arXiv:2104.04329
Video Object SegmentationonDAVIS (no YouTube-VOS training)
D17 val (G)· 2021-04-09
75.2
best: 80.4 (HMMN)
Learning Position and Target Consistency for Memory-based Video Object Segmentation arXiv:2104.04329
Video Object SegmentationonDAVIS (no YouTube-VOS training)
D17 val (J)· 2021-04-09
73.1
best: 77.7 (HMMN)
Learning Position and Target Consistency for Memory-based Video Object Segmentation arXiv:2104.04329
Video Object SegmentationonDAVIS (no YouTube-VOS training)
FPS· 2021-04-09
8.47
best: 50.1 (TBD)
Learning Position and Target Consistency for Memory-based Video Object Segmentation arXiv:2104.04329
Semi-Supervised Video Object SegmentationonDAVIS (no YouTube-VOS training)
D17 val (F)· 2021-04-09
77.2
best: 83.1 (HMMN)
Learning Position and Target Consistency for Memory-based Video Object Segmentation arXiv:2104.04329
Semi-Supervised Video Object SegmentationonDAVIS (no YouTube-VOS training)
D17 val (G)· 2021-04-09
75.2
best: 80.4 (HMMN)
Learning Position and Target Consistency for Memory-based Video Object Segmentation arXiv:2104.04329
Semi-Supervised Video Object SegmentationonDAVIS (no YouTube-VOS training)
D17 val (J)· 2021-04-09
73.1
best: 77.7 (HMMN)
Learning Position and Target Consistency for Memory-based Video Object Segmentation arXiv:2104.04329
Semi-Supervised Video Object SegmentationonDAVIS (no YouTube-VOS training)
FPS· 2021-04-09
8.47
best: 50.1 (TBD)
Learning Position and Target Consistency for Memory-based Video Object Segmentation arXiv:2104.04329

Audio6 results

10-shot image generationonDrawBench
Human Preference Alignement (HPSv2)· 2023-10-06
0.261
SOTA
Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference arXiv:2310.04378
1 Image, 2*2 StitchionDrawBench
Human Preference Alignement (HPSv2)· 2023-10-06
0.261
SOTA
Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference arXiv:2310.04378
10-shot image generationonDrawBench
Aesthetics (Laion Aesthtetics Predictor)· 2023-10-06
5.8038
best: 6.1829 (LCM (Curriculum DPO))
Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference arXiv:2310.04378
10-shot image generationonDrawBench
Text Alignement (SentenceBERT)· 2023-10-06
0.5602
best: 0.6234 (Stable Diffusion 1.5 (Curriculum DPO))
Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference arXiv:2310.04378
1 Image, 2*2 StitchionDrawBench
Aesthetics (Laion Aesthtetics Predictor)· 2023-10-06
5.8038
best: 6.1829 (LCM (Curriculum DPO))
Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference arXiv:2310.04378
1 Image, 2*2 StitchionDrawBench
Text Alignement (SentenceBERT)· 2023-10-06
0.5602
best: 0.6234 (Stable Diffusion 1.5 (Curriculum DPO))
Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference arXiv:2310.04378

Medical3 results

Image GenerationonDrawBench
Human Preference Alignement (HPSv2)· 2023-10-06
0.261
SOTA
Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference arXiv:2310.04378
Image GenerationonDrawBench
Aesthetics (Laion Aesthtetics Predictor)· 2023-10-06
5.8038
best: 6.1829 (LCM (Curriculum DPO))
Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference arXiv:2310.04378
Image GenerationonDrawBench
Text Alignement (SentenceBERT)· 2023-10-06
0.5602
best: 0.6234 (Stable Diffusion 1.5 (Curriculum DPO))
Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference arXiv:2310.04378

Natural Language Processing3 results

Text-to-Image GenerationonDrawBench
Human Preference Alignement (HPSv2)· 2023-10-06
0.261
SOTA
Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference arXiv:2310.04378
Text-to-Image GenerationonDrawBench
Aesthetics (Laion Aesthtetics Predictor)· 2023-10-06
5.8038
best: 6.1829 (LCM (Curriculum DPO))
Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference arXiv:2310.04378
Text-to-Image GenerationonDrawBench
Text Alignement (SentenceBERT)· 2023-10-06
0.5602
best: 0.6234 (Stable Diffusion 1.5 (Curriculum DPO))
Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference arXiv:2310.04378