相关论文: Filter Pruning by Switching to Neighboring CNNs wi…

Filter pruning of a CNN is typically achieved by applying discrete masks on the CNN's filter weights or activation maps, post-training. Here, we present a new filter-importance-scoring concept named pruning by active attention manipulation…

High image resolution is critical to obtain a good performance in many computer vision applications. Computational complexity of CNNs, however, grows significantly with the increase in input image size. Here, we show that it is almost…

Network pruning is an important research field aiming at reducing computational costs of neural networks. Conventional approaches follow a fixed paradigm which first trains a large and redundant network, and then determines which units…

Model-based deep learning (MBDL) is a powerful methodology for designing deep models to solve imaging inverse problems. MBDL networks can be seen as iterative algorithms that estimate the desired image using a physical measurement model and…

Channel pruning is a popular technique for compressing convolutional neural networks (CNNs), where various pruning criteria have been proposed to remove the redundant filters. From our comprehensive experiments, we found two blind spots in…

Though network pruning receives popularity in reducing the complexity of convolutional neural networks (CNNs), it remains an open issue to concurrently maintain model accuracy as well as achieve significant speedups on general CPUs. In this…

This paper presents a novel approach to neural network compression that addresses redundancy at both the filter and architectural levels through a unified framework grounded in information flow analysis. Building on the concept of tensor…

Artificial neural networks (ANNs) especially deep convolutional networks are very popular these days and have been proved to successfully offer quite reliable solutions to many vision problems. However, the use of deep neural networks is…

Deep neural networks (DNNs) have achieved remarkable success in object detection tasks, but their increasing complexity poses significant challenges for deployment on resource-constrained platforms. While model compression techniques such…

Nowadays, it is still difficult to adapt Convolutional Neural Network (CNN) based models for deployment on embedded devices. The heavy computation and large memory footprint of CNN models become the main burden in real application. In this…

Kernel pruning methods have been proposed to speed up, simplify, and improve explanation of convolutional neural network (CNN) models. However, the effectiveness of a simplified model is often below the original one. In this letter, we…

Most neural network pruning methods, such as filter-level and layer-level prunings, prune the network model along one dimension (depth, width, or resolution) solely to meet a computational budget. However, such a pruning policy often leads…

Pruning neural networks, i.e., removing some of their parameters whilst retaining their accuracy, is one of the main ways to reduce the latency of a machine learning pipeline, especially in resource- and/or bandwidth-constrained scenarios.…

The learning capability of a neural network improves with increasing depth at higher computational costs. Wider layers with dense kernel connectivity patterns furhter increase this cost and may hinder real-time inference. We propose feature…

Structured channel pruning has been shown to significantly accelerate inference time for convolution neural networks (CNNs) on modern hardware, with a relatively minor loss of network accuracy. Recent works permanently zero these channels…

Deep Convolutional Neural Networks have achieved state of the art performance across various computer vision tasks, however their practical deployment is limited by computational and memory overhead. This paper introduces Differential…

Pruning is a highly effective approach for compressing large language models (LLMs), significantly reducing inference latency. However, conventional training-free structured pruning methods often employ a heuristic metric that…

Current structural pruning methods face two significant limitations: (i) they often limit pruning to finer-grained levels like channels, making aggressive parameter reduction challenging, and (ii) they focus heavily on parameter and FLOP…

This paper presents an efficient and robust approach for reducing the size of deep neural networks by pruning entire neurons. It exploits maxout units for combining neurons into more complex convex functions and it makes use of a local…

Filter pruning is widely used to reduce the computation of deep learning, enabling the deployment of Deep Neural Networks (DNNs) in resource-limited devices. Conventional Hard Filter Pruning (HFP) method zeroizes pruned filters and stops…