相关论文: Low-Resource Vision Challenges for Foundation Mode…

Deep neural networks and huge language models are becoming omnipresent in natural language applications. As they are known for requiring large amounts of training data, there is a growing body of work to improve the performance in…

We survey applications of pretrained foundation models in robotics. Traditional deep learning models in robotics are trained on small datasets tailored for specific tasks, which limits their adaptability across diverse applications. In…

With promising yet saturated results in high-resource settings, low-resource datasets have gradually become popular benchmarks for evaluating the learning ability of advanced neural networks (e.g., BigBench, superGLUE). Some models even…

Generalization to unseen degradations remains a fundamental challenge for low-level vision models. This paper aims to investigate the underlying mechanism of this failure, using image deraining as a primary case study due to its…

Scene text recognition in low-resource languages frequently faces challenges due to the limited availability of training datasets derived from real-world scenes. This study proposes a novel approach that generates text images in…

In recent years, vision-language models have made significant strides, excelling in tasks like optical character recognition and geometric problem-solving. However, several critical issues remain: 1) Proprietary models often lack…

Recent studies show that large language models (LLMs) are powerful tools for working with natural language, bringing advances in many areas of computational linguistics. However, these models face challenges when applied to low-resource…

Foundation models have garnered increasing attention for representation learning in remote sensing. Many such foundation models adopt approaches that have demonstrated success in computer vision with minimal domain-specific modification.…

With impressive results in applications relying on feature learning, deep learning has also blurred the line between algorithm and data. Pick a training dataset, pick a backbone network for feature extraction, and voil\`a ; this usually…

Foundation models constitute a significant advancement in computer vision: after a single, albeit costly, training phase, they can address a wide array of tasks. In the field of Earth observation, over 75 remote sensing vision foundation…

Vision foundation models, which have demonstrated significant potential in many multimedia applications, are often underutilized in the natural sciences. This is primarily due to mismatches between the nature of domain-specific scientific…

Material classification has emerged as a critical task in computer vision and graphics, supporting the assignment of accurate material properties to a wide range of digital and real-world applications. While traditionally framed as an image…

Foundation models have advanced machine learning across various modalities, including images. Recently multiple teams trained foundation models specialized for remote sensing applications. This line of research is motivated by the distinct…

The inference-time resource costs of large language and vision models present a growing challenge in production deployments. We propose the use of foundation model programs, i.e., programs that can invoke foundation models with varying…

Real-world applications of natural language processing (NLP) are challenging. NLP models rely heavily on supervised machine learning and require large amounts of annotated data. These resources are often based on language data available in…

Image filters are fast, lightweight and effective, which make these conventional wisdoms preferable as basic tools in vision tasks. In practical scenarios, users have to tweak parameters multiple times to obtain satisfied results. This…

Low level image restoration is an integral component of modern artificial intelligence (AI) driven camera pipelines. Most of these frameworks are based on deep neural networks which present a massive computational overhead on resource…

Despite excellent results on benchmarks over a small subset of languages, large language models struggle to process text from languages situated in `lower-resource' scenarios such as dialects/sociolects (national or social varieties of a…

The advent of Large Language Models (LLMs) has significantly advanced the field of automated code generation. LLMs rely on large and diverse datasets to learn syntax, semantics, and usage patterns of programming languages. For low-resource…

How to achieve neural machine translation with limited parallel data? Existing techniques often rely on large-scale monolingual corpora, which is impractical for some low-resource languages. In this paper, we turn to connect several…