Related papers: DLF: Extreme Image Compression with Dual-generativ…

We tackle the common challenge of inter-concept visual confusion in compositional concept generation using text-guided diffusion models (TGDMs). It becomes even more pronounced in the generation of customized concepts, due to the scarcity…

Deep neural networks have demonstrated highly competitive performance in super-resolution (SR) for natural images by learning mappings from low-resolution (LR) to high-resolution (HR) images. However, hyperspectral super-resolution remains…

Compressed sensing MRI is a classic inverse problem in the field of computational imaging, accelerating the MR imaging by measuring less k-space data. The deep neural network models provide the stronger representation ability and faster…

Deep clustering which adopts deep neural networks to obtain optimal representations for clustering has been widely studied recently. In this paper, we propose a novel deep image clustering framework to learn a category-style latent…

The integration of extensive, dynamic knowledge into Large Language Models (LLMs) remains a significant challenge due to the inherent entanglement of factual data and reasoning patterns. Existing solutions, ranging from non-parametric…

Semantic segmentation is a key technology for autonomous vehicles to understand the surrounding scenes. The appealing performances of contemporary models usually come at the expense of heavy computations and lengthy inference time, which is…

Recent endeavors in Multimodal Large Language Models (MLLMs) aim to unify visual comprehension and generation by combining LLM and diffusion models, the state-of-the-art in each task, respectively. Existing approaches rely on spatial visual…

Fine-tuning plays a crucial role in enabling pre-trained LLMs to evolve from general language comprehension to task-specific expertise. To preserve user data privacy, federated fine-tuning is often employed and has emerged as the de facto…

Large Language Models (LLMs) face computational inefficiencies and redundant processing when handling long context inputs, prompting a focus on compression techniques. While existing semantic vector-based compression methods achieve…

Deeply learned representations have achieved superior image retrieval performance in a retrieve-then-rerank manner. Recent state-of-the-art single stage model, which heuristically fuses local and global features, achieves promising…

Recent advances on Multi-modal Large Language Models have demonstrated that high-resolution image input is crucial for model capabilities, especially for fine-grained tasks. However, high-resolution images lead to a quadratic increase in…

With the continuous improvement of device imaging resolution, the popularity of Ultra-High-Definition (UHD) images is increasing. Unfortunately, existing methods for fusing multi-exposure images in dynamic scenes are designed for…

We propose Deep Lossless Image Coding (DLIC), a full resolution learned lossless image compression algorithm. Our algorithm is based on a neural network combined with an entropy encoder. The neural network performs a density estimation on…

In the domain of image generation, latent-based generative models occupy a dominant status; however, these models rely heavily on image tokenizer. To meet modeling requirements, autoregressive models possessing the characteristics of…

Binary quantization approaches, which replace weight matrices with binary matrices and substitute costly multiplications with cheaper additions, offer a computationally efficient approach to address the increasing computational and storage…

Deep neural networks (DNNs) have become indispensable in many real-life applications like natural language processing, and autonomous systems. However, deploying DNNs on resource-constrained devices, e.g., in RISC-V platforms, remains…

We present a novel paradigm for ultra-low-bitrate image compression (ULB-IC) that exploits the "temporal" evolution in generative image compression. Specifically, we define an explicit intermediate state during decoding: a compact anchor…

We propose a novel concept of dual and integrated latent topologies (DITTO in short) for implicit 3D reconstruction from noisy and sparse point clouds. Most existing methods predominantly focus on single latent type, such as point or grid…

Recent works on neural network pruning advocate that reducing the depth of the network is more effective in reducing run-time memory usage and accelerating inference latency than reducing the width of the network through channel pruning. In…

Fine-tuning a pre-trained language model (PLM) emerges as the predominant strategy in many natural language processing applications. However, this process is known to be expensive, especially on edge devices with low computing power. While…