相关论文: L2PF -- Learning to Prune Faster

Building compact convolutional neural networks (CNNs) with reliable performance is a critical but challenging task, especially when deploying them in real-world applications. As a common approach to reduce the size of CNNs, pruning methods…

Structure pruning is an effective method to compress and accelerate neural networks. While filter and channel pruning are preferable to other structure pruning methods in terms of realistic acceleration and hardware compatibility, pruning…

The enormous inference cost of deep neural networks can be scaled down by network compression. Pruning is one of the predominant approaches used for deep network compression. However, existing pruning techniques have one or more of the…

Convolutional neural networks have shown tremendous performance capabilities in computer vision tasks, but their excessive amounts of weight storage and arithmetic operations prevent them from being adopted in embedded environments. One of…

Convolutional Neural Networks (CNNs) filter the input data using spatial convolution operators with compact stencils. Commonly, the convolution operators couple features from all channels, which leads to immense computational cost in the…

Video generation, while capable of generating realistic videos, is computationally expensive and slow, prohibiting real-time applications. In this paper, we observe that video latents encoded via an autoencoder under the Latent Diffusion…

Magnitude Pruning is a staple lightweight network design method which seeks to remove connections with the smallest magnitude. This process is either achieved in a structured or unstructured manner. While structured pruning allows reaching…

Deep neural networks (DNNs) have become a widely deployed model for numerous machine learning applications. However, their fixed architecture, substantial training cost, and significant model redundancy make it difficult to efficiently…

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…

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…

Deep neural networks are typically too computationally expensive to run in real-time on consumer-grade hardware and low-powered devices. In this paper, we investigate reducing the computational and memory requirements of neural networks…

Despite the promising results of convolutional neural networks (CNNs), their application on devices with limited resources is still a big challenge; this is mainly due to the huge memory and computation requirements of the CNN. To counter…

Structured pruning methods are developed to bridge the gap between the massive scale of neural networks and the limited hardware resources. Most current structured pruning methods rely on training datasets to fine-tune the compressed model,…

Neural network pruning is a widely used strategy for reducing model storage and computing requirements. It allows to lower the complexity of the network by introducing sparsity in the weights. Because taking advantage of sparse matrices is…

To compress deep convolutional neural networks (CNNs) with large memory footprint and long inference time, this paper proposes a novel pruning criterion using layer-wised Ln-norm of feature maps. Different from existing pruning criteria,…

Graph convolutional networks (GCNs) are nowadays becoming mainstream in solving many image processing tasks including skeleton-based recognition. Their general recipe consists in learning convolutional and attention layers that maximize…

Pruning methods have shown to be effective at reducing the size of deep neural networks while keeping accuracy almost intact. Among the most effective methods are those that prune a network while training it with a sparsity prior loss and…

Convolutional neural networks (CNNs) have emerged as the state-of-the-art in multiple vision tasks including depth estimation. However, memory and computing power requirements remain as challenges to be tackled in these models. Monocular…

We introduce a DNN training technique that learns only a fraction of the full parameter set without incurring an accuracy penalty. To do this, our algorithm constrains the total number of weights updated during backpropagation to those with…

This paper considers a convolutional neural network transformation that reduces computation complexity and thus speedups neural network processing. Usage of convolutional neural networks (CNN) is the standard approach to image recognition…