Related papers: DGQ: Distribution-Aware Group Quantization for Tex…

Novel diffusion models can synthesize photo-realistic images with integrated high-quality text. Surprisingly, we demonstrate through attention activation patching that only less than $1$% of diffusion models' parameters, all contained in…

Text-to-image synthesis has made significant progress, benefiting from the strong generative capabilities of diffusion models. However, these models struggle to achieve precise text-to-image alignment within cross-attention maps during the…

Network quantization is an effective method for the deployment of neural networks on memory and energy constrained mobile devices. In this paper, we propose a Dynamic Network Quantization (DNQ) framework which is composed of two modules: a…

Image compression techniques have made remarkable progress when it comes to file size reduction with a tolerable quality reduction; nonetheless, they are facing some challenges when it comes to applying more compression with the same…

Diffusion models have demonstrated significant applications in the field of image generation. However, their high computational and memory costs pose challenges for deployment. Model quantization has emerged as a promising solution to…

Large language models (LLMs) deliver strong performance, but their high compute and memory costs make deployment difficult in resource-constrained scenarios. Weight-only post-training quantization (PTQ) is appealing, as it reduces memory…

Diffusion Transformers (DiTs) have emerged as the state-of-the-art backbone for high-fidelity image and video generation. However, their massive computational cost and memory footprint hinder deployment on edge devices. While post-training…

Inference for state-of-the-art deep neural networks is computationally expensive, making them difficult to deploy on constrained hardware environments. An efficient way to reduce this complexity is to quantize the weight parameters and/or…

Neural network quantization is an effective way to compress deep models and improve their execution latency and energy efficiency, so that they can be deployed on mobile or embedded devices. Existing quantization methods require original…

Vision Transformers (ViTs) are essential in computer vision but are computationally intensive, too. Model quantization, particularly to low bit-widths like 4-bit, aims to alleviate this difficulty, yet existing Post-Training Quantization…

Quantization-Aware Training (QAT) is a critical technique for deploying deep neural networks on resource-constrained devices. However, existing methods often face two major challenges: the highly non-uniform distribution of activations and…

In image processing, one of the most challenging tasks is to render an image's semantic meaning using a variety of artistic approaches. Existing techniques for arbitrary style transfer (AST) frequently experience mode-collapse,…

Diffusion models have achieved cutting-edge performance in image generation. However, their lengthy denoising process and computationally intensive score estimation network impede their scalability in low-latency and resource-constrained…

The emergence of visual autoregressive (AR) models has revolutionized image generation while presenting new challenges for synthetic image detection. Unlike previous GAN or diffusion-based methods, AR models generate images through discrete…

This research focuses on the development and enhancement of text-to-image denoising diffusion models, addressing key challenges such as limited sample diversity and training instability. By incorporating Classifier-Free Guidance (CFG) and…

Video diffusion models (DMs) have enabled high-quality video synthesis. Yet, their substantial computational and memory demands pose serious challenges to real-world deployment, even on high-end GPUs. As a commonly adopted solution,…

The instability in GAN training has been a long-standing problem despite remarkable research efforts. We identify that instability issues stem from difficulties of performing feature matching with mini-batch statistics, due to a fragile…

Diffusion models have recently emerged as the dominant approach in visual generation tasks. However, the lengthy denoising chains and the computationally intensive noise estimation networks hinder their applicability in low-latency and…

This paper develops a unified framework for image-to-image translation based on conditional diffusion models and evaluates this framework on four challenging image-to-image translation tasks, namely colorization, inpainting, uncropping, and…

Hashing methods, which encode high-dimensional images with compact discrete codes, have been widely applied to enhance large-scale image retrieval. In this paper, we put forward Deep Spherical Quantization (DSQ), a novel method to make deep…