Foundation models like CLIP allow zero-shot transfer on various tasks without additional
training data. Yet, the zero-shot performance is less competitive than a fully supervised one …

Fine-tuning vision-language models (VLMs) like CLIP to downstream tasks is often
necessary to optimize their performance. However, a major obstacle is the limited availability …

The promising zero-shot generalization of vision-language models such as CLIP has led to
their adoption using prompt learning for numerous downstream tasks. Previous works have …

Zero-shot inference is a powerful paradigm that enables the use of large pretrained models
for downstream classification tasks without further training. However, these models are …

The promising zero-shot generalization of vision-language models such as CLIP has led to
their adoption using prompt learning for numerous downstream tasks. Previous works have …

Generative modeling has been the dominant approach for large-scale pretraining and zero-
shot generalization. In this work, we challenge this convention by showing that …

Zero-shot inference is a powerful paradigm that enables the use of large pretrained models
for downstream classification tasks without further training. However, these models are …

Abstract Out-of-distribution (OOD) generalization, where the model needs to handle
distribution shifts from training, is a major challenge of machine learning. Contrastive …

The conventional recipe for maximizing model accuracy is to (1) train multiple models with
various hyperparameters and (2) pick the individual model which performs best on a held …

Semantic-descriptor-based Generalized Zero-Shot Learning (GZSL) poses challenges in
recognizing novel classes in the test phase. The development of generative models enables …