Related papers: Training-Free Adaptive Quantization for Variable R…
Neural audio codecs, leveraging quantization algorithms, have significantly impacted various speech/audio tasks. While high-fidelity reconstruction is paramount for human perception, audio coding for machines (ACoM) prioritizes efficient…
In this paper, we study a new problem arising from the emerging MPEG standardization effort Video Coding for Machine (VCM), which aims to bridge the gap between visual feature compression and classical video coding. VCM is committed to…
The rapid development of Artificial Intelligence (AI) and Internet of Things (IoT) increases the requirement for edge computing with low power and relatively high processing speed devices. The Computing-In-Memory(CIM) schemes based on…
Residual Vector Quantization (RVQ) has become a dominant approach in neural speech and audio coding, providing high-fidelity compression. However, speech coding presents additional challenges due to real-world noise, which degrades…
Vision transformer emerges as a potential architecture for vision tasks. However, the intense computation and non-negligible delay hinder its application in the real world. As a widespread model compression technique, existing post-training…
We solve the analysis sparse coding problem considering a combination of convex and non-convex sparsity promoting penalties. The multi-penalty formulation results in an iterative algorithm involving proximal-averaging. We then unfold the…
Quantization-aware training (QAT) is a common paradigm for network quantization, in which the training phase incorporates the simulation of the low-precision computation to optimize the quantization parameters in alignment with the task…
Image Compression for Machines (ICM) has emerged as a pivotal research direction in the field of visual data compression. However, with the rapid evolution of machine intelligence, the target of compression has shifted from task-specific…
Recent neural compression methods have been based on the popular hyperprior framework. It relies on Scalar Quantization and offers a very strong compression performance. This contrasts from recent advances in image generation and…
Large language models (LLMs) are omnipresent, however their practical deployment is challenging due to their ever increasing computational and memory demands. Quantization is one of the most effective ways to make them more compute and…
This paper presents variable bitrate lossy image compression using a VAE-based neural network. An adaptable image quality adjustment strategy is proposed. The key innovation involves adeptly adjusting the input scale exclusively during the…
There has been a growing trend in compressing and transmitting videos from terminals for machine vision tasks. Nevertheless, most video coding optimization method focus on minimizing distortion according to human perceptual metrics,…
As neural networks gain widespread adoption in embedded devices, there is a need for model compression techniques to facilitate deployment in resource-constrained environments. Quantization is one of the go-to methods yielding…
This paper proposes a novel framework for rate-adaptive semantic communication based on multi-stage vector quantization (VQ), termed \textit{MSVQ-SC}. Unlike conventional single-stage VQ approaches, which require exponentially larger…
Recently it has been shown that deep learning-based image compression has shown the potential to outperform traditional codecs. However, most existing methods train multiple networks for multiple bit rates, which increases the…
Computing-in-Memory (CIM) accelerators are a promising solution for accelerating Machine Learning (ML) workloads, as they perform Matrix-Vector Multiplications (MVMs) on crossbar arrays directly in memory. Although the bit widths of the…
With the increasing scale of machine learning tasks, it has become essential to reduce the communication between computing nodes. Early work on gradient compression focused on the bottleneck between CPUs and GPUs, but…
Although image super-resolution (SR) problem has experienced unprecedented restoration accuracy with deep neural networks, it has yet limited versatile applications due to the substantial computational costs. Since different input images…
Post-training quantization (PTQ) has stood out as a cost-effective and promising model compression paradigm in recent years, as it avoids computationally intensive model retraining. Nevertheless, current PTQ methods for Vision Transformers…
Network quantization generally converts full-precision weights and/or activations into low-bit fixed-point values in order to accelerate an inference process. Recent approaches to network quantization further discretize the gradients into…