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/AltCLIP

AltCLIP

Reported on 16 benchmarks across 2 tasks · 1 paper · 5 SOTA

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

Computer Vision10 results

Zero-Shot Transfer Image ClassificationonCN-ImageNet V2
Accuracy (Private)· 2022-11-12
50.9
SOTA
AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities arXiv:2211.06679
Zero-Shot Transfer Image ClassificationonCN-ImageNet
Accuracy (Private)· 2022-11-12
59.6
best: 64.5 (InternVL-C)
SOTA
AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities arXiv:2211.06679
Zero-Shot Transfer Image ClassificationonCN-ImageNet-A
Accuracy (Private)· 2022-11-12
58.5
SOTA
AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities arXiv:2211.06679
Zero-Shot Transfer Image ClassificationonCN-ImageNet-Sketch
Accuracy (Private)· 2022-11-12
46.5
SOTA
AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities arXiv:2211.06679
Zero-Shot Transfer Image ClassificationonCN-ImageNet-R
Accuracy (Private)· 2022-11-12
79.9
SOTA
AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities arXiv:2211.06679
Zero-Shot Transfer Image ClassificationonImageNet V2
Accuracy (Private)· 2022-11-12
68.1
best: 81.2 (BASIC (Lion))
AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities arXiv:2211.06679
Zero-Shot Transfer Image ClassificationonImageNet-A
Accuracy (Private)· 2022-11-12
69.5
best: 90.2 (CoCa)
AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities arXiv:2211.06679
Zero-Shot Transfer Image ClassificationonImageNet
Accuracy (Private)· 2022-11-12
74.5
best: 88.5 (M2-Encoder)
AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities arXiv:2211.06679
Zero-Shot Transfer Image ClassificationonImageNet-R
Accuracy· 2022-11-12
87.2
best: 96.8 (BASIC (Lion))
AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities arXiv:2211.06679
Zero-Shot Transfer Image ClassificationonImageNet-Sketch
Accuracy (Private)· 2022-11-12
58.7
best: 77.6 (CoCa)
AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities arXiv:2211.06679

Miscellaneous6 results

Image Retrieval with Multi-Modal QueryonFlickr30k
Image-to-text R@1· 2022-11-12
86
best: 98.8 (X2-VLM (large))
AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities arXiv:2211.06679
Image Retrieval with Multi-Modal QueryonFlickr30k
Image-to-text R@10· 2022-11-12
99.1
best: 100 (X2-VLM (large))
AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities arXiv:2211.06679
Image Retrieval with Multi-Modal QueryonFlickr30k
Image-to-text R@5· 2022-11-12
98
best: 100 (X2-VLM (large))
AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities arXiv:2211.06679
Image Retrieval with Multi-Modal QueryonFlickr30k
Text-to-image R@1· 2022-11-12
72.5
best: 93.3 (ERNIE-ViL 2.0)
AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities arXiv:2211.06679
Image Retrieval with Multi-Modal QueryonFlickr30k
Text-to-image R@10· 2022-11-12
95.4
best: 99.8 (ERNIE-ViL 2.0)
AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities arXiv:2211.06679
Image Retrieval with Multi-Modal QueryonFlickr30k
Text-to-image R@5· 2022-11-12
91.6
best: 99.5 (M2-Encoder)
AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities arXiv:2211.06679