相关论文: Data-Free Dynamic Compression of CNNs for Tractabl…

Tucker decomposition is one of the SOTA CNN model compression techniques. However, unlike the FLOPs reduction, we observe very limited inference time reduction with Tucker-compressed models using existing GPU software such as cuDNN. To this…

Structured network pruning excels non-structured methods because they can take advantage of the thriving developed parallel computing techniques. In this paper, we propose a new structured pruning method. Firstly, to create more structured…

Network Pruning is a promising way to address the huge computing resource demands of the deployment and inference of Large Language Models (LLMs). Retraining-free is important for LLMs' pruning methods. However, almost all of the existing…

The state-of-the-art performance for several real-world problems is currently reached by convolutional neural networks (CNN). Such learning models exploit recent results in the field of deep learning, typically leading to highly performing,…

The rapid advancement of deep learning in medical image analysis has greatly enhanced the accuracy of skin cancer classification. However, current state-of-the-art models, especially those based on transfer learning like ResNet50, come with…

Making deep convolutional neural networks more accurate typically comes at the cost of increased computational and memory resources. In this paper, we reduce this cost by exploiting the fact that the importance of features computed by…

Due to their growing popularity and computational cost, deep neural networks (DNNs) are being targeted for hardware acceleration. A popular architecture for DNN acceleration, adopted by the Google Tensor Processing Unit (TPU), utilizes a…

We propose a novel approach to reduce the computational cost of evaluation of convolutional neural networks, a factor that has hindered their deployment in low-power devices such as mobile phones. Inspired by the loop perforation technique…

Neural network pruning offers a promising prospect to facilitate deploying deep neural networks on resource-limited devices. However, existing methods are still challenged by the training inefficiency and labor cost in pruning designs, due…

With the good performance of deep learning algorithms in the field of computer vision (CV), the convolutional neural network (CNN) architecture has become a main backbone of the computer vision task. With the widespread use of mobile…

We reduce training time in convolutional networks (CNNs) with a method that, for some of the mini-batches: a) scales down the resolution of input images via downsampling, and b) reduces the forward pass operations via pooling on the…

Homomorphic Encryption (HE), allowing computations on encrypted data (ciphertext) without decrypting it first, enables secure but prohibitively slow Convolutional Neural Network (CNN) inference for privacy-preserving applications in clouds.…

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…

Hardware acceleration for dilated and transposed convolution enables real time execution of related tasks like segmentation, but current designs are specific for these convolutional types or suffer from complex control for reconfigurable…

The computational demands of computer vision tasks based on state-of-the-art Convolutional Neural Network (CNN) image classification far exceed the energy budgets of mobile devices. This paper proposes FixyNN, which consists of a…

Existing methods for reducing the computational burden of neural networks at run-time, such as parameter pruning or dynamic computational path selection, focus solely on improving computational efficiency during inference. On the other…

We present a computationally efficient method for compressing a trained neural network without using real data. We break the problem of data-free network compression into independent layer-wise compressions. We show how to efficiently…

Neural Networks (NN), although successfully applied to several Artificial Intelligence tasks, are often unnecessarily over-parametrised. In edge/fog computing, this might make their training prohibitive on resource-constrained devices,…

Soft filter pruning~(SFP) has emerged as an effective pruning technique for allowing pruned filters to update and the opportunity for them to regrow to the network. However, this pruning strategy applies training and pruning in an…

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…