Related papers: Image Coding for Machines with Omnipotent Feature …

In-context learning (ICL) enables efficient few-shot learning in large language models (LLMs) without training, but suffers from the quadratic input complexity of transformers, limiting the maximum number of exemplars. While various…

In-context learning (ICL) enables large language models (LLMs) to adapt to new tasks without weight updates by learning from demonstration sequences. While ICL shows strong empirical performance, its internal representational mechanisms are…

Intrinsic image decomposition, which is an essential task in computer vision, aims to infer the reflectance and shading of the scene. It is challenging since it needs to separate one image into two components. To tackle this, conventional…

In-context learning (ICL) is one of the most powerful and most unexpected capabilities to emerge in recent transformer-based large language models (LLMs). Yet the mechanisms that underlie it are poorly understood. In this paper, we…

Image transformation, a class of vision and graphics problems whose goal is to learn the mapping between an input image and an output image, develops rapidly in the context of deep neural networks. In Computer Vision (CV), many problems can…

Existing Multimodal Large Language Models (MLLMs) process a large number of visual tokens, leading to significant computational costs and inefficiency. Instruction-related visual token compression demonstrates strong task relevance, which…

Deep learning model inference on embedded devices is challenging due to the limited availability of computation resources. A popular alternative is to perform model inference on the cloud, which requires transmitting images from the…

Real world image super-resolution (Real-ISR) often leverages the powerful generative priors of text-to-image diffusion models by regularizing the output to lie on their learned manifold. However, existing methods often overlook the…

Current learned image compression models typically exhibit high complexity, which demands significant computational resources. To overcome these challenges, we propose an innovative approach that employs hierarchical feature extraction…

The recently proposed Multilinear Compressive Learning (MCL) framework combines Multilinear Compressive Sensing and Machine Learning into an end-to-end system that takes into account the multidimensional structure of the signals when…

The paper deals with Video Coding for Machines that is a new paradigm in video coding related to consumption of decoded video by humans and machines. For such tasks, joint transmission of compressed video and features is considered. In this…

Lossy image compression is one of the most commonly used operators for digital images. Most recently proposed deep-learning-based image compression methods leverage the auto-encoder structure, and reach a series of promising results in this…

Conventional image compression methods typically aim at pixel-level consistency while ignoring the performance of downstream AI tasks.To solve this problem, this paper proposes a Semantic-Assisted Image Compression method (SAIC), which can…

In-Context Learning (ICL) empowers Large Language Models (LLMs) with the ability to learn from a few examples provided in the prompt, enabling downstream generalization without the requirement for gradient updates. Despite encouragingly…

In this paper we deal with image classification tasks using the powerful CLIP vision-language model. Our goal is to advance the classification performance using the CLIP's image encoder, by proposing a novel Large Multimodal Model (LMM)…

Learning-based image compression methods have emerged as state-of-the-art, showcasing higher performance compared to conventional compression solutions. These data-driven approaches aim to learn the parameters of a neural network model…

Despite the impressive performance of large multimodal models (LMMs) in high-level visual tasks, their capacity for image quality assessment (IQA) remains limited. One main reason is that LMMs are primarily trained for high-level tasks…

Data-driven artificial intelligence (AI) techniques are becoming prominent for learning in support of data compression, but are focused on standard problems such as text compression. To instead address the emerging problem of semantic…

The efficient coding hypothesis proposes that the response properties of sensory systems are adapted to the statistics of their inputs such that they capture maximal information about the environment, subject to biological constraints.…

Video coding algorithms encode and decode an entire video frame while feature coding techniques only preserve and communicate the most critical information needed for a given application. This is because video coding targets human…