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/M3I Pre-training (InternImage-H)

M3I Pre-training (InternImage-H)

Reported on 14 benchmarks across 7 tasks · 1 paper

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

Methodology8 results

3DonCOCO test-dev
box mAP· 2022-11-17
65.4
best: 66 (Co-DETR)
Towards All-in-one Pre-training via Maximizing Multi-modal Mutual Information arXiv:2211.09807
3DonCOCO minival
box AP· uses extra data· 2022-11-17
65
best: 66 (PE_spatial (DETA))
Towards All-in-one Pre-training via Maximizing Multi-modal Mutual Information arXiv:2211.09807
2D ClassificationonCOCO test-dev
box mAP· 2022-11-17
65.4
best: 66 (Co-DETR)
Towards All-in-one Pre-training via Maximizing Multi-modal Mutual Information arXiv:2211.09807
2D ClassificationonCOCO minival
box AP· uses extra data· 2022-11-17
65
best: 66 (PE_spatial (DETA))
Towards All-in-one Pre-training via Maximizing Multi-modal Mutual Information arXiv:2211.09807
2D Object DetectiononCOCO test-dev
box mAP· 2022-11-17
65.4
best: 66 (Co-DETR)
Towards All-in-one Pre-training via Maximizing Multi-modal Mutual Information arXiv:2211.09807
2D Object DetectiononCOCO minival
box AP· uses extra data· 2022-11-17
65
best: 66 (PE_spatial (DETA))
Towards All-in-one Pre-training via Maximizing Multi-modal Mutual Information arXiv:2211.09807
16konCOCO test-dev
box mAP· 2022-11-17
65.4
best: 66 (Co-DETR)
Towards All-in-one Pre-training via Maximizing Multi-modal Mutual Information arXiv:2211.09807
16konCOCO minival
box AP· uses extra data· 2022-11-17
65
best: 66 (PE_spatial (DETA))
Towards All-in-one Pre-training via Maximizing Multi-modal Mutual Information arXiv:2211.09807

Medical2 results

Semantic SegmentationonADE20K
Params (M)· uses extra data· 2022-11-17
1310
best: 3000 (FD-SwinV2-G)
Towards All-in-one Pre-training via Maximizing Multi-modal Mutual Information arXiv:2211.09807
Semantic SegmentationonADE20K
Validation mIoU· uses extra data· 2022-11-17
62.9
best: 63.6 (ViT-P (InternImage-H))
Towards All-in-one Pre-training via Maximizing Multi-modal Mutual Information arXiv:2211.09807

Computer Vision2 results

Object DetectiononCOCO test-dev
box mAP· 2022-11-17
65.4
best: 66 (Co-DETR)
Towards All-in-one Pre-training via Maximizing Multi-modal Mutual Information arXiv:2211.09807
Object DetectiononCOCO minival
box AP· uses extra data· 2022-11-17
65
best: 66 (PE_spatial (DETA))
Towards All-in-one Pre-training via Maximizing Multi-modal Mutual Information arXiv:2211.09807

Audio2 results

10-shot image generationonADE20K
Params (M)· uses extra data· 2022-11-17
1310
best: 3000 (FD-SwinV2-G)
Towards All-in-one Pre-training via Maximizing Multi-modal Mutual Information arXiv:2211.09807
10-shot image generationonADE20K
Validation mIoU· uses extra data· 2022-11-17
62.9
best: 63.6 (ViT-P (InternImage-H))
Towards All-in-one Pre-training via Maximizing Multi-modal Mutual Information arXiv:2211.09807