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/InternImage-XL

InternImage-XL

Reported on 27 benchmarks across 9 tasks · 1 paper · 2 SOTA

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

Methodology12 results

3DonCOCO test-dev
Params (M)· 2022-11-10
602
best: 3000 (SwinV2-G (HTC++))
InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions arXiv:2211.05778
3DonCOCO test-dev
box mAP· 2022-11-10
64.3
best: 66 (Co-DETR)
InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions arXiv:2211.05778
3DonCOCO minival
box AP· uses extra data· 2022-11-10
64.2
best: 66 (PE_spatial (DETA))
InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions arXiv:2211.05778
2D ClassificationonCOCO test-dev
Params (M)· 2022-11-10
602
best: 3000 (SwinV2-G (HTC++))
InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions arXiv:2211.05778
2D ClassificationonCOCO test-dev
box mAP· 2022-11-10
64.3
best: 66 (Co-DETR)
InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions arXiv:2211.05778
2D ClassificationonCOCO minival
box AP· uses extra data· 2022-11-10
64.2
best: 66 (PE_spatial (DETA))
InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions arXiv:2211.05778
2D Object DetectiononCOCO test-dev
Params (M)· 2022-11-10
602
best: 3000 (SwinV2-G (HTC++))
InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions arXiv:2211.05778
2D Object DetectiononCOCO test-dev
box mAP· 2022-11-10
64.3
best: 66 (Co-DETR)
InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions arXiv:2211.05778
2D Object DetectiononCOCO minival
box AP· uses extra data· 2022-11-10
64.2
best: 66 (PE_spatial (DETA))
InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions arXiv:2211.05778
16konCOCO test-dev
Params (M)· 2022-11-10
602
best: 3000 (SwinV2-G (HTC++))
InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions arXiv:2211.05778
16konCOCO test-dev
box mAP· 2022-11-10
64.3
best: 66 (Co-DETR)
InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions arXiv:2211.05778
16konCOCO minival
box AP· uses extra data· 2022-11-10
64.2
best: 66 (PE_spatial (DETA))
InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions arXiv:2211.05778

Computer Vision7 results

Instance SegmentationonCOCO minival
GFLOPs· 2022-11-10
1782
SOTA
InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions arXiv:2211.05778
Instance SegmentationonCOCO minival
Params (M)· 2022-11-10
387
SOTA
InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions arXiv:2211.05778
Object DetectiononCOCO test-dev
Params (M)· 2022-11-10
602
best: 3000 (SwinV2-G (HTC++))
InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions arXiv:2211.05778
Object DetectiononCOCO test-dev
box mAP· 2022-11-10
64.3
best: 66 (Co-DETR)
InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions arXiv:2211.05778
Object DetectiononCOCO minival
box AP· uses extra data· 2022-11-10
64.2
best: 66 (PE_spatial (DETA))
InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions arXiv:2211.05778
Image ClassificationonImageNet
GFLOPs· 2022-11-10
163
best: 1478 (InternImage-H)
InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions arXiv:2211.05778
Instance SegmentationonCOCO minival
mask AP· 2022-11-10
48.8
best: 56.6 (Co-DETR)
InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions arXiv:2211.05778

Medical4 results

Semantic SegmentationonCityscapes val
mIoU· uses extra data· 2022-11-10
86.4
best: 90.3 (EfficientPS (Cityscapes-fine))
InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions arXiv:2211.05778
Semantic SegmentationonADE20K
GFLOPs· 2022-11-10
3142
best: 4635 (InternImage-H)
InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions arXiv:2211.05778
Semantic SegmentationonADE20K
Params (M)· 2022-11-10
368
best: 3000 (FD-SwinV2-G)
InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions arXiv:2211.05778
Semantic SegmentationonADE20K
Validation mIoU· 2022-11-10
55.3
best: 63.6 (ViT-P (InternImage-H))
InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions arXiv:2211.05778

Audio4 results

10-shot image generationonCityscapes val
mIoU· uses extra data· 2022-11-10
86.4
best: 90.3 (EfficientPS (Cityscapes-fine))
InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions arXiv:2211.05778
10-shot image generationonADE20K
GFLOPs· 2022-11-10
3142
best: 4635 (InternImage-H)
InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions arXiv:2211.05778
10-shot image generationonADE20K
Params (M)· 2022-11-10
368
best: 3000 (FD-SwinV2-G)
InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions arXiv:2211.05778
10-shot image generationonADE20K
Validation mIoU· 2022-11-10
55.3
best: 63.6 (ViT-P (InternImage-H))
InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions arXiv:2211.05778