Related papers: APPLeNet: Visual Attention Parameterized Prompt Le…

The evolution of prompt learning methodologies has driven exploration of deeper prompt designs to enhance model performance. However, current deep text prompting approaches suffer from two critical limitations: Over-reliance on constrastive…

Prompt learning has proven effective in adapting vision language models for downstream tasks. However, existing methods usually append learnable prompt tokens solely with the category names to obtain textual features, which fails to fully…

Vision-language models (VLMs) can learn high-quality representations from a large-scale training dataset of image-text pairs. Prompt learning is a popular approach to fine-tuning VLM to adapt them to downstream tasks. Despite the satisfying…

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…

Although large-scale labeled data are essential for deep convolutional neural networks (ConvNets) to learn high-level semantic visual representations, it is time-consuming and impractical to collect and annotate large-scale datasets. A…

Recent advances in large pre-trained vision-language models have demonstrated remarkable performance on zero-shot downstream tasks. Building upon this, recent studies, such as CoOp and CoCoOp, have proposed the use of prompt learning, where…

The advancement of vision-language models, particularly the Contrastive Language-Image Pre-training (CLIP) model, has revolutionized the field of machine learning by enabling robust zero-shot learning capabilities. These capabilities allow…

Vision-language models (VLMs) pre-trained on web-scale data exhibit promising zero-shot generalization but often suffer from semantic misalignment due to domain gaps between pre-training and downstream tasks. Existing approaches primarily…

The goal of few-shot learning is to recognize new visual concepts with just a few amount of labeled samples in each class. Recent effective metric-based few-shot approaches employ neural networks to learn a feature similarity comparison…

Large Vision and Language Models (LVLMs) have shown strong performance across various vision-language tasks in natural image domains. However, their application to remote sensing (RS) remains underexplored due to significant domain…

Most of the achievements in artificial intelligence so far were accomplished by supervised learning which requires numerous annotated training data and thus costs innumerable manpower for labeling. Unsupervised learning is one of the…

Recent advances in multimodal learning has resulted in powerful vision-language models, whose representations are generalizable across a variety of downstream tasks. Recently, their generalization ability has been further extended by…

Few-shot visual recognition refers to recognize novel visual concepts from a few labeled instances. Many few-shot visual recognition methods adopt the metric-based meta-learning paradigm by comparing the query representation with class…

Weakly supervised semantic segmentation (WSSS) approaches typically rely on class activation maps (CAMs) for initial seed generation, which often fail to capture global context due to limited supervision from image-level labels. To address…

Generalized Zero-shot Semantic Segmentation aims to segment both seen and unseen categories only under the supervision of the seen ones. To tackle this, existing methods adopt the large-scale Vision Language Models (VLMs) which obtain…

Recent Vision-Language Models (VLMs) have demonstrated remarkable multimodal understanding capabilities, yet the redundant visual tokens incur prohibitive computational overhead and degrade inference efficiency. Prior studies typically…

Remote sensing data is often distributed across multiple institutions, and due to privacy concerns and data-sharing restrictions, leveraging large-scale datasets in a centralized training framework is challenging. Federated learning offers…

Vision-Language Models (VLMs), particularly CLIP, have revolutionized anomaly detection by enabling zero-shot and few-shot defect identification without extensive labeled datasets. By learning aligned representations of images and text,…

Vision-and-Language Navigation (VLN) aims to develop intelligent agents to navigate in unseen environments only through language and vision supervision. In the recently proposed continuous settings (continuous VLN), the agent must act in a…

In visual recognition tasks, few-shot learning requires the ability to learn object categories with few support examples. Its re-popularity in light of the deep learning development is mainly in image classification. This work focuses on…