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/InternVL-C

InternVL-C

Reported on 26 benchmarks across 4 tasks · 1 paper · 1 SOTA

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

Computer Vision13 results

Zero-Shot Transfer Image ClassificationonCN-ImageNet
Accuracy (Private)· 2023-12-21
64.5
SOTA
InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks arXiv:2312.14238
Zero-Shot Transfer Image ClassificationonImageNet V2
Accuracy (Private)· 2023-12-21
77.3
best: 81.2 (BASIC (Lion))
InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks arXiv:2312.14238
Zero-Shot Transfer Image ClassificationonImageNet-A
Accuracy (Private)· 2023-12-21
83.8
best: 90.2 (CoCa)
InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks arXiv:2312.14238
Zero-Shot Transfer Image ClassificationonImageNet
Accuracy (Private)· 2023-12-21
83.2
best: 88.5 (M2-Encoder)
InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks arXiv:2312.14238
Zero-Shot Transfer Image ClassificationonFood-101
Top 1 Accuracy· 2023-12-21
95.3
best: 96.2 (MAWS (ViT-2B))
InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks arXiv:2312.14238
Zero-Shot Transfer Image ClassificationonObjectNet
Accuracy (Private)· 2023-12-21
80.6
best: 87.6 (LiT-22B)
InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks arXiv:2312.14238
Zero-Shot Transfer Image ClassificationonImageNet-Sketch
Accuracy (Private)· 2023-12-21
73.9
best: 77.6 (CoCa)
InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks arXiv:2312.14238
Zero-Shot Video RetrievalonMSR-VTT-full
text-to-video R@1· 2023-12-21
44.7
best: 46.3 (InternVL-G)
InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks arXiv:2312.14238
Zero-Shot Video RetrievalonMSR-VTT-full
text-to-video R@10· 2023-12-21
78.4
best: 79.6 (InternVL-G)
InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks arXiv:2312.14238
Zero-Shot Video RetrievalonMSR-VTT-full
text-to-video R@5· 2023-12-21
68.2
best: 70.5 (InternVL-G)
InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks arXiv:2312.14238
Zero-Shot Video RetrievalonMSR-VTT-full
video-to-text R@1· 2023-12-21
40.2
best: 64.7 (VideoCoCa)
InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks arXiv:2312.14238
Zero-Shot Video RetrievalonMSR-VTT-full
video-to-text R@10· 2023-12-21
74.1
best: 91.4 (VideoCoCa)
InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks arXiv:2312.14238
Zero-Shot Video RetrievalonMSR-VTT-full
video-to-text R@5· 2023-12-21
63.1
best: 85.2 (VideoCoCa)
InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks arXiv:2312.14238

Miscellaneous12 results

Image Retrieval with Multi-Modal QueryonFlickr30k
Image-to-text R@1· 2023-12-21
94.7
best: 98.8 (X2-VLM (large))
InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks arXiv:2312.14238
Image Retrieval with Multi-Modal QueryonFlickr30k
Image-to-text R@10· 2023-12-21
99.9
best: 100 (X2-VLM (large))
InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks arXiv:2312.14238
Image Retrieval with Multi-Modal QueryonFlickr30k
Image-to-text R@5· 2023-12-21
99.6
best: 100 (X2-VLM (large))
InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks arXiv:2312.14238
Image Retrieval with Multi-Modal QueryonFlickr30k
Text-to-image R@1· 2023-12-21
81.7
best: 93.3 (ERNIE-ViL 2.0)
InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks arXiv:2312.14238
Image Retrieval with Multi-Modal QueryonFlickr30k
Text-to-image R@10· 2023-12-21
98.2
best: 99.8 (ERNIE-ViL 2.0)
InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks arXiv:2312.14238
Image Retrieval with Multi-Modal QueryonFlickr30k
Text-to-image R@5· 2023-12-21
96
best: 99.5 (M2-Encoder)
InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks arXiv:2312.14238
Image Retrieval with Multi-Modal QueryonCOCO 2014
Image-to-text R@1· 2023-12-21
70.6
best: 84.8 (BEiT-3)
InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks arXiv:2312.14238
Image Retrieval with Multi-Modal QueryonCOCO 2014
Image-to-text R@10· 2023-12-21
93.5
best: 98.5 (X2-VLM (large))
InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks arXiv:2312.14238
Image Retrieval with Multi-Modal QueryonCOCO 2014
Image-to-text R@5· 2023-12-21
89
best: 96.5 (X2-VLM (large))
InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks arXiv:2312.14238
Image Retrieval with Multi-Modal QueryonCOCO 2014
Text-to-image R@1· 2023-12-21
54.1
best: 68 (VAST)
InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks arXiv:2312.14238
Image Retrieval with Multi-Modal QueryonCOCO 2014
Text-to-image R@10· 2023-12-21
84.6
best: 92.8 (VAST)
InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks arXiv:2312.14238
Image Retrieval with Multi-Modal QueryonCOCO 2014
Text-to-image R@5· 2023-12-21
77.3
best: 92.8 (BEiT-3)
InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks arXiv:2312.14238

Natural Language Processing1 result

Visual Question Answering (VQA)onVQA v2 test-dev
Accuracy· 2023-12-21
81.2
best: 84.3 (PaLI)
InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks arXiv:2312.14238