Vision-language models enable open-world classification of objects without the need for any
retraining. While this zero-shot paradigm marks a significant advance, even today's best …

Large pre-trained vision-language models such as CLIP provide compact and general-
purpose representations of text and images that are demonstrably effective across multiple …

Large pre-trained vision-language models such as CLIP provide compact and general-
purpose representations of text and images that are demonstrably effective across multiple …

Foundational vision-language models such as CLIP are becoming a new paradigm in
vision, due to their excellent generalization abilities. However, adapting these models for …

Vision-language foundation models have exhibited remarkable success across a multitude
of downstream tasks due to their scalability on extensive image-text paired datasets …

Vision-language model (VLM) embeddings have been shown to encode biases present in
their training data, such as societal biases that prescribe negative characteristics to …

Popular zero-shot models suffer due to artifacts inherited from pretraining. One particularly
detrimental issue, caused by unbalanced web-scale pretraining data, is mismatched label …

Vision-language models (VLMs), eg, CLIP, have shown remarkable potential in zero-shot
image classification. However, adapting these models to new domains remains challenging …

We propose a novel prompt tuning method called CoAPT (Context Attribute words in Prompt
Tuning) for few/zero-shot image classification. The core motivation is that attributes are …

Popular zero-shot models suffer due to artifacts inherited from pretraining. A particularly
detrimental artifact, caused by unbalanced web-scale pretraining data, is mismatched label …