Embracing Diversity: Interpretable Zero-shot classification beyond one vector per class

arXiv:2404.16717v1 Announce Type: new
Abstract: 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 models exhibit skewed performance when objects are dissimilar from their typical depiction. Real world objects such as pears appear in a variety of forms -- from diced to whole, on a table or in a bowl -- yet standard VLM classifiers map all instances of a class to a \it{single vector …

abstract advance arxiv beyond class classification cs.ai cs.cv cs.hc diversity language language models marks objects open-world paradigm per performance retraining type vector vision vision-language vision-language models while world zero-shot