Related papers: ShiftLIC: Lightweight Learned Image Compression wi…
Vision-language pre-training like CLIP has shown promising performance on various downstream tasks such as zero-shot image classification and image-text retrieval. Most of the existing CLIP-alike works usually adopt relatively large image…
Singular Value Decomposition (SVD) has recently seen a surge of interest as a simple yet powerful tool for large language models (LLMs) compression, with a growing number of works demonstrating 20-80% parameter reductions at minimal…
There has been much interest in deploying deep learning algorithms on low-powered devices, including smartphones, drones, and medical sensors. However, full-scale deep neural networks are often too resource-intensive in terms of energy and…
Neural image compression (NIC) usually adopts a predefined family of probabilistic distributions as the prior of the latent variables, and meanwhile relies on entropy models to estimate the parameters for the probabilistic family. More…
Recent advancements in deep learning have driven significant progress in lossless image compression. With the emergence of Large Language Models (LLMs), preliminary attempts have been made to leverage the extensive prior knowledge embedded…
Large vision-language models (LVLMs) achieve strong multimodal understanding, but their inference cost grows rapidly with the number of visual tokens, especially for high-resolution images and long videos. Existing attention-based methods…
Recent advances in learned image compression (LIC) have enabled practical deployments, spurring active research into image compression for machines and progressive coding schemes. However, their integration remains under-explored: prior…
Window-based transformers have demonstrated outstanding performance in super-resolution tasks due to their adaptive modeling capabilities through local self-attention (SA). However, they exhibit higher computational complexity and inference…
Learning-based video compression has been extensively studied over the past years, but it still has limitations in adapting to various motion patterns and entropy models. In this paper, we propose multi-mode video compression (MMVC), a…
Convolutional neural networks (CNNs) have become increasingly difficult to deploy in resource-constrained environments due to their large memory and computational requirements. Although low-rank compression methods can reduce this burden,…
Light-Field (LF) image is emerging 4D data of light rays that is capable of realistically presenting spatial and angular information of 3D scene. However, the large data volume of LF images becomes the most challenging issue in real-time…
This paper presents a module, Spatial Cross-scale Convolution (SCSC), which is verified to be effective in improving both CNNs and Transformers. Nowadays, CNNs and Transformers have been successful in a variety of tasks. Especially for…
Large language models (LLMs) have spurred development in multiple industries. However, the growing number of their parameters brings substantial storage and computing burdens, making it essential to explore model compression techniques for…
In controllable image synthesis, generating coherent and consistent images from multiple references with spatial layout awareness remains an open challenge. We present LAMIC, a Layout-Aware Multi-Image Composition framework that, for the…
The increasing complexity of neural networks poses a significant barrier to the deployment of distributed machine learning (ML) on resource-constrained devices, such as federated learning (FL). Split learning (SL) offers a promising…
As an increasing amount of image and video content will be analyzed by machines, there is demand for a new codec paradigm that is capable of compressing visual input primarily for the purpose of computer vision inference, while secondarily…
Deep learning-based image compression (LIC) has achieved state-of-the-art rate-distortion (RD) performance, yet deploying these models on resource-constrained FPGAs remains a major challenge. This work presents a complete, multi-stage…
Surveillance and security scenarios usually require high efficient facial image compression scheme for face recognition and identification. While either traditional general image codecs or special facial image compression schemes only…
In the realm of deep learning, spatial attention mechanisms have emerged as a vital method for enhancing the performance of convolutional neural networks. However, these mechanisms possess inherent limitations that cannot be overlooked.…
While Large Vision-Language Models (LVLMs) demonstrate exceptional multi-modal capabilities, the quadratic computational cost of processing high-resolution visual tokens remains a critical bottleneck. Though recent token reduction…