Finetuning image-text models such as CLIP achieves state-of-the-art accuracies on a variety
of benchmarks. However, recent works (Kumar et al., 2022; Wortsman et al., 2021) have …

In this paper, we leverage CLIP for zero-shot sketch based image retrieval (ZS-SBIR). We
are largely inspired by recent advances on foundation models and the unparalleled …

A long-standing goal of AI systems is to perform complex multimodal reasoning like humans.
Recently, large language models (LLMs) have made remarkable strides in such multi-step …

Large vision models with billions of parameters and trained on broad data have great
potential in numerous downstream applications. However, these models are typically difficult …

Recently, growing interest has been aroused in extending the multimodal capability of large
language models (LLMs), eg, vision-language (VL) learning, which is regarded as the next …

Abstract In Composed Image Retrieval (CIR), a user combines a query image with text to
describe their intended target. Existing methods rely on supervised learning of CIR models …

Learning visual representations from natural language supervision has recently shown great
promise in a number of pioneering works. In general, these language-augmented visual …

Abstract Out-of-distribution (OOD) detection refers to training the model on in-distribution (ID)
dataset to classify if the input images come from unknown classes. Considerable efforts …

We propose a novel unsupervised backlit image enhancement method, abbreviated as CLIP-
LIT, by exploring the potential of Contrastive Language-Image Pre-Training (CLIP) for pixel …

Prompt tuning, a parameter-and data-efficient transfer learning paradigm that tunes only a
small number of parameters in a model's input space, has become a trend in the vision …