Related papers: Bridging the Training-Deployment Gap: Gated Encodi…

Diffusion models have achieved significant visual generation quality. However, their significant computational and memory costs pose challenge for their application on resource-constrained mobile devices or even desktop GPUs. Recent…

Quantization is an effective technique to reduce memory footprint, inference latency, and power consumption of deep learning models. However, existing quantization methods suffer from accuracy degradation compared to full-precision (FP)…

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…

Quantization-aware training (QAT) is typically performed for a single target numeric format, while practical deployments often need to choose numerical precision at inference time based on hardware support or runtime constraints. We study…

Product Quantization (PQ) has long been a mainstream for generating an exponentially large codebook at very low memory/time cost. Despite its success, PQ is still tricky for the decomposition of high-dimensional vector space, and the…

In an unpaired setting, lacking sufficient content constraints for image-to-image translation (I2I) tasks, GAN-based approaches are usually prone to model collapse. Current solutions can be divided into two categories, reconstruction-based…

The training of deep neural networks (DNNs) always requires intensive resources for both computation and data storage. Thus, DNNs cannot be efficiently applied to mobile phones and embedded devices, which severely limits their applicability…

Image super-resolution is a common task on mobile and IoT devices, where one often needs to upscale and enhance low-resolution images and video frames. While numerous solutions have been proposed for this problem in the past, they are…

Medical images usually suffer from image degradation in clinical practice, leading to decreased performance of deep learning-based models. To resolve this problem, most previous works have focused on filtering out degradation-causing…

The design of image and video quality assessment (QA) algorithms is extremely important to benchmark and calibrate user experience in modern visual systems. A major drawback of the state-of-the-art QA methods is their limited ability to…

Recently, vision transformers (ViTs) have superseded convolutional neural networks in numerous applications, including classification, detection, and segmentation. However, the high computational requirements of ViTs hinder their widespread…

Due to numerous hardware shortcomings, medical image acquisition devices are susceptible to producing low-quality (i.e., low contrast, inappropriate brightness, noisy, etc.) images. Regrettably, perceptually degraded images directly impact…

Quantization for deep neural networks (DNN) have enabled developers to deploy models with less memory and more efficient low-power inference. However, not all DNN designs are friendly to quantization. For example, the popular Mobilenet…

Under limited data setting, GANs often struggle to navigate and effectively exploit the input latent space. Consequently, images generated from adjacent variables in a sparse input latent space may exhibit significant discrepancies in…

Despite the outstanding performance of transformers in both language and vision tasks, the expanding computation and model size have increased the demand for efficient deployment. To address the heavy computation and parameter drawbacks,…

Quantizing neural networks is one of the most effective methods for achieving efficient inference on mobile and embedded devices. In particular, mixed precision quantized (MPQ) networks, whose layers can be quantized to different bitwidths,…

A growing trend has emerged in designing high-quality Small Language Models (SLMs) with a few million parameters. This trend is driven by the increasing concerns over cloud costs, privacy, and latency. Considering that full parameter…

We consider the task of photo-realistic unconditional image generation (generate high quality, diverse samples that carry the same visual content as the image) on mobile platforms using Generative Adversarial Networks (GANs). In this paper,…

When training neural networks with simulated quantization, we observe that quantized weights can, rather unexpectedly, oscillate between two grid-points. The importance of this effect and its impact on quantization-aware training (QAT) are…

Multi-bit quantization networks enable flexible deployment of deep neural networks by supporting multiple precision levels within a single model. However, existing approaches suffer from significant training overhead as full-dataset updates…