Related papers: Q-Diffusion: Quantizing Diffusion Models

This paper introduces Distribution-Flexible Subset Quantization (DFSQ), a post-training quantization method for super-resolution networks. Our motivation for developing DFSQ is based on the distinctive activation distributions of current…

Diffusion models and flow-matching models have enabled generating diverse and realistic images by learning to transfer noise to data. However, sampling from these models involves iterative denoising over many neural network passes, making…

Diffusion transformers (DiTs) combine transformer architectures with diffusion models. However, their computational complexity imposes significant limitations on real-time applications and sustainability of AI systems. In this study, we aim…

With the great success of diffusion models in image generation, diffusion-based image compression is attracting increasing interests. However, due to the random noise introduced in the diffusion learning, they usually produce…

Diffusion models have emerged as powerful generative models, but their high computation cost in iterative sampling remains a significant bottleneck. In this work, we present an in-depth and insightful study of state-of-the-art acceleration…

Text-to-image generation via Stable Diffusion models (SDM) have demonstrated remarkable capabilities. However, their computational intensity, particularly in the iterative denoising process, hinders real-time deployment in latency-sensitive…

Post-training quantization (PTQ) improves efficiency but struggles with limited calibration data, especially under privacy constraints. Data-free quantization (DFQ) mitigates this by generating synthetic images using generative models such…

Diffusion models have demonstrated remarkable performance on vision generation tasks. However, the high computational complexity hinders its wide application on edge devices. Quantization has emerged as a promising technique for inference…

Post-training quantization (PTQ) has evolved as a prominent solution for compressing complex models, which advocates a small calibration dataset and avoids end-to-end retraining. However, most existing PTQ methods employ block-wise…

Despite the success of CNN models on a variety of Image classification and segmentation tasks, their extensive computational and storage demands pose considerable challenges for real-world deployment on resource-constrained devices.…

Although there have been significant advancements in image compression techniques, such as standard and learned codecs, these methods still suffer from severe quality degradation at extremely low bits per pixel. While recent diffusion-based…

Inference time, model size, and accuracy are three key factors in deep model compression. Most of the existing work addresses these three key factors separately as it is difficult to optimize them all at the same time. For example, low-bit…

Diffusion Transformers (DiTs) have emerged as a highly scalable and effective backbone for image generation, outperforming U-Net architectures in both scalability and performance. However, their real-world deployment remains challenging due…

Incorporating diffusion models in the image compression domain has the potential to produce realistic and detailed reconstructions, especially at extremely low bitrates. Previous methods focus on using diffusion models as expressive…

Deep neural networks have achieved state-of-the-art results in a wide range of applications, from natural language processing and computer vision to speech recognition. However, as tasks become increasingly complex, model sizes continue to…

Diffusion transformers (DiT) have demonstrated exceptional performance in video generation. However, their large number of parameters and high computational complexity limit their deployment on edge devices. Quantization can reduce storage…

Significant investments have been made towards the commodification of diffusion models for generation of diverse media. Their mass-market adoption is however still hobbled by the intense hardware resource requirements of diffusion model…

Large Language Models (LLMs) suffer severe performance degradation when facing extremely low-bit (sub 2-bit) quantization. Several existing sub 2-bit post-training quantization (PTQ) methods utilize a mix-precision scheme by leveraging an…

Network quantization significantly reduces model inference complexity and has been widely used in real-world deployments. However, most existing quantization methods have been developed mainly on Convolutional Neural Networks (CNNs), and…

With the rapid increase in the size of neural networks, model compression has become an important area of research. Quantization is an effective technique at decreasing the model size, memory access, and compute load of large models.…