Related papers: Causality-guided Prompt Learning for Vision-langua…

Continual learning of vision-language models (VLMs) focuses on leveraging cross-modal pretrained knowledge to incrementally adapt to expanding downstream tasks and datasets, while tackling the challenge of knowledge forgetting. Existing…

Visual explanation (attention)-guided learning uses not only labels but also explanations to guide model reasoning process. While visual attention-guided learning has shown promising results, it requires a large number of explanation…

As a fundamental and extensively studied task in computer vision, image segmentation aims to locate and identify different semantic concepts at the pixel level. Recently, inspired by In-Context Learning (ICL), several generalist…

Pre-trained vision-language models like CLIP have shown powerful zero-shot inference ability via image-text matching and prove to be strong few-shot learners in various downstream tasks. However, in real-world scenarios, adapting CLIP to…

Language-vision models like CLIP have made significant strides in vision tasks, such as zero-shot image classification (ZSIC). However, generating specific and expressive visual descriptions remains challenging; descriptions produced by…

Vision-language models (VLMs) have demonstrated exceptional generalization capabilities for downstream tasks. Due to its efficiency, prompt learning has gradually become a more effective and efficient method for transferring VLMs to…

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 a single image perturbation such that a frozen model prompted…

Most existing vision-language pre-training methods focus on understanding tasks and use BERT-like objectives (masked language modeling and image-text matching) during pretraining. Although they perform well in many understanding downstream…

Existing computer vision research in artwork struggles with artwork's fine-grained attributes recognition and lack of curated annotated datasets due to their costly creation. To the best of our knowledge, we are one of the first methods to…

Graph neural networks stand as the predominant technique for graph representation learning owing to their strong expressive power, yet the performance highly depends on the availability of high-quality labels in an end-to-end manner. Thus…

Class-incremental learning (CIL) enables models to learn new classes progressively while preserving knowledge of previously learned ones. Recent advances in this field have shifted towards parameter-efficient fine-tuning techniques, with…

Contrastive Language-Image Pre-training (CLIP) has been shown to learn visual representations with great transferability, which achieves promising accuracy for zero-shot classification. To further improve its downstream performance,…

Prompt learning is one of the most effective and trending ways to adapt powerful vision-language foundation models like CLIP to downstream datasets by tuning learnable prompt vectors with very few samples. However, although prompt learning…

Contrastive Language-Image Pre-training (CLIP) has drawn increasing attention recently for its transferable visual representation learning. However, due to the semantic gap within datasets, CLIP's pre-trained image-text alignment becomes…

Recently, the contrastive language-image pre-training, e.g., CLIP, has demonstrated promising results on various downstream tasks. The pre-trained model can capture enriched visual concepts for images by learning from a large scale of…

Existing pedestrian attribute recognition (PAR) algorithms adopt pre-trained CNN (e.g., ResNet) as their backbone network for visual feature learning, which might obtain sub-optimal results due to the insufficient employment of the…

Surgical phase recognition is a critical component for context-aware decision support in intelligent operating rooms, yet training robust models is hindered by limited annotated clinical videos and large domain gaps between synthetic and…

With the advent of large-scale pre-trained models, interest in adapting and exploiting them for continual learning scenarios has grown. In this paper, we propose an approach to exploiting pre-trained vision-language models (e.g. CLIP) that…

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 community since the emergence of large vision-language models…

This work aims to adapt large-scale pre-trained vision-language models, such as contrastive language-image pretraining (CLIP), to enhance the performance of object reidentification (Re-ID) across various supervision settings. Although…