AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities

Benchmark Model Rank Results
zero-shot-transfer-image-classification-on-imagenet-sketchAltCLIP#8Accuracy (Private): 58.7
zero-shot-transfer-image-classification-on-imagenet-v2AltCLIP#10Accuracy (Private): 68.1
zero-shot-transfer-image-classification-on-imagenet-rAltCLIP#13Accuracy: 87.2
zero-shot-transfer-image-classification-on-imagenetAltCLIP#14Accuracy (Private): 74.5
zero-shot-transfer-image-classification-on-imagenet-aAltCLIP#14Accuracy (Private): 69.5
zero-shot-cross-modal-retrieval-on-flickr30kAltCLIP#19Image-to-text R@1: 86Image-to-text R@5: 98Image-to-text R@10: 99.1…
zero-shot-cross-modal-retrieval-on-coco-2014AltCLIP#23Image-to-text R@1: 58.6
image-classification-on-imagenet-v2AltCLIP#47Top 1 Accuracy: 68.2