Deep models, eg, CNNs and Vision Transformers, have achieved impressive achievements
in many vision tasks in the closed world. However, novel classes emerge from time to time in …

When transferring a pretrained model to a downstream task, two popular methods are full
fine-tuning (updating all the model parameters) and linear probing (updating only the last …

Well-designed prompts can guide text-to-image models to generate amazing images.
However, the performant prompts are often model-specific and misaligned with user input …

Fine-tuning large pre-trained models on downstream tasks has been adopted in a variety of
domains recently. However, it is costly to update the entire parameter set of large pre-trained …

Large pre-trained models such as CLIP or ALIGN offer consistent accuracy across a range of
data distributions when performing zero-shot inference (ie, without fine-tuning on a specific …

Recently, fine-tuning language models pre-trained on large text corpora have provided huge
improvements on vision-and-language (V&L) tasks as well as on pure language tasks …

Recent text-to-image generation models have shown promising results in generating high-
fidelity photo-realistic images. Though the results are astonishing to human eyes, how …

Prompt learning has emerged as an efficient alternative for fine-tuning foundational models,
such as CLIP, for various downstream tasks. Conventionally trained using the task-specific …

Image-based visual-language (I-VL) pre-training has shown great success for learning joint
visual-textual representations from large-scale web data, revealing remarkable ability for …

We investigate the efficacy of visual prompting to adapt large-scale models in vision.
Following the recent approach from prompt tuning and adversarial reprogramming, we learn …