相关论文: A Survey of Low-shot Vision-Language Model Adaptat…

Few-shot Learning aims to learn and distinguish new categories with a very limited number of available images, presenting a significant challenge in the realm of deep learning. Recent researchers have sought to leverage the additional…

Traditionally, kernel methods rely on the representer theorem which states that the solution to a learning problem is obtained as a linear combination of the data mapped into the reproducing kernel Hilbert space (RKHS). While elegant from…

The adaptation of large-scale Vision-Language Models (VLMs) like CLIP to downstream tasks with extremely limited data -- specifically in the one-shot regime -- is often hindered by a significant "Stability-Plasticity" dilemma. While…

Motivated by the growing interest in representation learning approaches that uncover the latent structure of high-dimensional data, this work proposes new algorithms for reconstruction-based manifold learning within Reproducing-Kernel…

Few-shot learning aims to train models that can be generalized to novel classes with only a few samples. Recently, a line of works are proposed to enhance few-shot learning with accessible semantic information from class names. However,…

By describing the features and abstractions of our world, language is a crucial tool for human learning and a promising source of supervision for machine learning models. We use language to improve few-shot visual classification in the…

We develop a mathematical framework to address a broad class of metric and preference learning problems within a Hilbert space. We obtain a novel representer theorem for the simultaneous task of metric and preference learning. Our key…

Few-shot models aim at making predictions using a minimal number of labeled examples from a given task. The main challenge in this area is the one-shot setting where only one element represents each class. We propose HyperShot - the fusion…

In this paper, we look at the problem of few-shot classification that aims to learn a classifier for previously unseen classes and domains from few labeled samples. Recent methods use adaptation networks for aligning their features to new…

Integrating image and text data through multi-modal learning has emerged as a new approach in medical imaging research, following its successful deployment in computer vision. While considerable efforts have been dedicated to establishing…

Large-scale Vision-Language Foundation Models (VLFMs), such as CLIP, now underpin a wide range of computer vision research and applications. VLFMs are often adapted to various domain-specific tasks. However, VLFM performance on novel,…

Recent advances in large language and vision-language models have enabled strong reasoning capabilities, yet they remain impractical for specialized domains like remote sensing, where annotated data is scarce and expensive. We present the…

The existing few-shot video classification methods often employ a meta-learning paradigm by designing customized temporal alignment module for similarity calculation. While significant progress has been made, these methods fail to focus on…

Few-shot learning performs classification tasks and regression tasks on scarce samples. As one of the most representative few-shot learning models, Prototypical Network represents each class as sample average, or a prototype, and measures…

As the boosting development of large vision-language models like Contrastive Language-Image Pre-training (CLIP), many CLIP-like methods have shown impressive abilities on visual recognition, especially in low-data regimes scenes. However,…

Few-shot learning is a challenging problem that has attracted more and more attention recently since abundant training samples are difficult to obtain in practical applications. Meta-learning has been proposed to address this issue, which…

Low-shot image classification is a fundamental task in computer vision, and the emergence of large-scale vision-language models such as CLIP has greatly advanced the forefront of research in this field. However, most existing CLIP-based…

Transformer-based models have dominated natural language processing and other areas in the last few years due to their superior (zero-shot) performance on benchmark datasets. However, these models are poorly understood due to their…

This paper presents a general vector-valued reproducing kernel Hilbert spaces (RKHS) framework for the problem of learning an unknown functional dependency between a structured input space and a structured output space. Our formulation…

The growing popularity of Contrastive Language-Image Pretraining (CLIP) has led to its widespread application in various visual downstream tasks. To enhance CLIP's effectiveness and versatility, efficient few-shot adaptation techniques have…