相关论文: Layer-adaptive Structured Pruning Guided by Latenc…

In this work, we propose a graph-adaptive pruning (GAP) method for efficient inference of convolutional neural networks (CNNs). In this method, the network is viewed as a computational graph, in which the vertices denote the computation…

Structured pruning is a popular method to reduce the cost of convolutional neural networks, that are the state of the art in many computer vision tasks. However, depending on the architecture, pruning introduces dimensional discrepancies…

Pruning before training enables the deployment of neural networks on smart devices. By retaining weights conducive to generalization, pruned networks can be accommodated on resource-constrained smart devices. It is commonly held that the…

Despite the recent success of large language models (LLMs), LLMs are particularly challenging in long-sequence inference scenarios due to the quadratic computational complexity of the attention mechanism. Inspired by the interpretability…

We propose a novel hardware-aware magnitude pruning technique for coherent photonic neural networks. The proposed technique can prune 99.45% of network parameters and reduce the static power consumption by 98.23% with a negligible accuracy…

Intracortical brain-machine interfaces demand low-latency, energy-efficient solutions for neural decoding. Spiking Neural Networks (SNNs) deployed on neuromorphic hardware have demonstrated remarkable efficiency in neural decoding by…

To accelerate deep CNN models, this paper proposes a novel spatially adaptive framework that can dynamically generate pixel-wise sparsity according to the input image. The sparse scheme is pixel-wise refined, regional adaptive under a…

Diverse user preferences over images have recently led to a great amount of interest in controlling the imagery effects for image restoration tasks. However, existing methods require separate inference through the entire network per each…

Driven by significant improvements in architectural design and training pipelines, computer vision has recently experienced dramatic progress in terms of accuracy on classic benchmarks such as ImageNet. These highly-accurate models are…

One of the main challenges since the advancement of convolutional neural networks is how to connect the extracted feature map to the final classification layer. VGG models used two sets of fully connected layers for the classification part…

Large Language Models (LLMs) have achieved great success in solving difficult tasks across many domains, but such success comes with a high computation cost, and inference latency. As developers and third parties customize these models, the…

Spiking neural networks (SNNs) have manifested remarkable advantages in power consumption and event-driven property during the inference process. To take full advantage of low power consumption and improve the efficiency of these models…

Convolutional Neural Network (CNN) has an amount of parameter redundancy, filter pruning aims to remove the redundant filters and provides the possibility for the application of CNN on terminal devices. However, previous works pay more…

We introduce hybrid pruning which combines both coarse-grained channel and fine-grained weight pruning to reduce model size, computation and power demands with no to little loss in accuracy for enabling modern networks deployment on…

To reduce the significant redundancy in deep Convolutional Neural Networks (CNNs), most existing methods prune neurons by only considering statistics of an individual layer or two consecutive layers (e.g., prune one layer to minimize the…

With the introduction of SNIP [arXiv:1810.02340v2], it has been demonstrated that modern neural networks can effectively be pruned before training. Yet, its sensitivity criterion has since been criticized for not propagating training signal…

The subject of green AI has been gaining attention within the deep learning community given the recent trend of ever larger and more complex neural network models. Existing solutions for reducing the computational load of training at…

Pruning large language models (LLMs) is a promising solution for reducing model sizes and computational complexity while preserving performance. Traditional layer-wise pruning methods often adopt a uniform sparsity approach across all…

Unet and its variations have been standard in semantic image segmentation, especially for computer assisted radiology. Current Unet architectures iteratively downsample spatial resolution while increasing channel dimensions to preserve…

Network pruning has been the driving force for the acceleration of neural networks and the alleviation of model storage/transmission burden. With the advent of AutoML and neural architecture search (NAS), pruning has become topical with…