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/ONE-PEACE

ONE-PEACE

Reported on 19 benchmarks across 7 tasks · 1 paper · 12 SOTA

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

Audio9 results

Audio ClassificationonFSD50K
mAP· uses extra data· 2023-05-18
69.7
SOTA
ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities arXiv:2305.11172
10-shot image generationonADE20K
Validation mIoU· uses extra data· 2023-05-18
63
best: 63.6 (ViT-P (InternImage-H))
SOTA
ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities arXiv:2305.11172
Text to Audio RetrievalonAudioCaps
R@1· uses extra data· 2023-05-18
42.5
best: 55.2 (InternVideo2-6B)
SOTA
ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities arXiv:2305.11172
Text to Audio RetrievalonAudioCaps
R@10· uses extra data· 2023-05-18
88.4
SOTA
ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities arXiv:2305.11172
Text to Audio RetrievalonAudioCaps
R@5· uses extra data· 2023-05-18
77.5
SOTA
ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities arXiv:2305.11172
Text to Audio RetrievalonClotho
R@1· uses extra data· 2023-05-18
22.4
best: 27.69 (PaSST-RoBERTa & Estimated Audio–Caption Correspondences)
SOTA
ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities arXiv:2305.11172
Text to Audio RetrievalonClotho
R@10· uses extra data· 2023-05-18
62.7
best: 70.39 (PaSST-RoBERTa & Estimated Audio–Caption Correspondences)
SOTA
ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities arXiv:2305.11172
Text to Audio RetrievalonClotho
R@5· uses extra data· 2023-05-18
49
best: 57.03 (PaSST-RoBERTa & Estimated Audio–Caption Correspondences)
SOTA
ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities arXiv:2305.11172
10-shot image generationonADE20K
Params (M)· uses extra data· 2023-05-18
1500
best: 3000 (FD-SwinV2-G)
ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities arXiv:2305.11172

Natural Language Processing5 results

Visual Question Answering (VQA)onVQA v2 test-std
number· 2023-05-18
72.24
SOTA
ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities arXiv:2305.11172
Visual Question Answering (VQA)onVQA v2 test-std
yes/no· 2023-05-18
94.85
SOTA
ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities arXiv:2305.11172
Visual Question Answering (VQA)onVQA v2 test-dev
Accuracy· 2023-05-18
82.6
best: 84.3 (PaLI)
ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities arXiv:2305.11172
Visual Question Answering (VQA)onVQA v2 test-std
other· 2023-05-18
74.15
best: 77.02 (mPLUG-Huge)
ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities arXiv:2305.11172
Visual Question Answering (VQA)onVQA v2 test-std
overall· 2023-05-18
82.52
best: 84.03 (BEiT-3)
ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities arXiv:2305.11172

Medical2 results

Semantic SegmentationonADE20K
Validation mIoU· uses extra data· 2023-05-18
63
best: 63.6 (ViT-P (InternImage-H))
SOTA
ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities arXiv:2305.11172
Semantic SegmentationonADE20K
Params (M)· uses extra data· 2023-05-18
1500
best: 3000 (FD-SwinV2-G)
ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities arXiv:2305.11172

Computer Vision2 results

VideoonKinetics-400
Acc@1· 2023-05-18
88.1
best: 93.6 (OmniVec2)
ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities arXiv:2305.11172
VideoonKinetics-400
Acc@5· 2023-05-18
97.8
best: 98.9 (TubeViT-H (ImageNet-1k))
ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities arXiv:2305.11172

Methodology1 result

ClassificationonFSD50K
mAP· uses extra data· 2023-05-18
69.7
SOTA
ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities arXiv:2305.11172