Thanks to the large pre-trained vision-language models (VLMs) like CLIP, we can craft a
zero-shot classifier by discrete prompt design, eg, the confidence score of an image …

Prompt tuning represents a valuable technique for adapting pre-trained visual-language
models (VLM) to various downstream tasks. Recent advancements in CoOp-based methods …

Abstract Diffusion Models (DMs) have emerged as powerful generative models with
unprecedented image generation capability. These models are widely used for data …

Although soft prompt tuning is effective in efficiently adapting Vision-Language (V&L)
models for downstream tasks it shows limitations in dealing with distribution shifts. We …

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 a visual pre-trained model can leverage the semantic information from large-
scale pre-training data and mitigate the over-fitting problem on downstream vision tasks with …

Large pre-trained vision-language models, such as CLIP [Radford et al. 2021], have
demonstrated remarkable performance in few-shot image classification. To facilitate the …

When fine-tuning zero-shot models like CLIP, our desideratum is for the fine-tuned model to
excel in both in-distribution (ID) and out-of-distribution (OOD). Recently, ensemble-based …

Vision-language models, like CLIP (Contrastive Language Image Pretraining), are
becoming increasingly popular for a wide range of multimodal retrieval tasks. However, prior …

Vision-language models such as CLIP are capable of map** the different modality data
into a unified feature space, enabling zero/few-shot inference by measuring the similarity of …