Results 1 to 10 of about 240 (107)
A-pruning: a lightweight pineapple flower counting network based on filter pruning
Complex & Intelligent Systems, 2023 During pineapple cultivation, detecting and counting the number of pineapple flowers in real time and estimating the yield are essential. Deep learning methods are more efficient in real-time performance than traditional manual detection.
Guoyan Yu +4 more
doaj +3 more sources
Filter Pruning via Measuring Feature Map Information
Sensors, 2021 Neural network pruning, an important method to reduce the computational complexity of deep models, can be well applied to devices with limited resources. However, most current methods focus on some kind of information about the filter itself to prune the
Linsong Shao +6 more
doaj +3 more sources
Filter Pruning Without Damaging Networks Capacity [PDF]
IEEE Access, 2020 Due to its over-parameterized design, the deep convolutional neural networks lead to a huge amount of parameters and high computational cost, making it difficult to deploy on some devices with limited computational resources in reality. In this paper, we
Yuding Zuo, Bo Chen, Te Shi, Mengfan Sun
doaj +2 more sources
Pruning Filters Base on Extending Filter Group Lasso [PDF]
IEEE Access, 2020 Deep Convolution Neural Networks (CNNs) have been widely used in image recognition, while models of CNNs are desired to be more compact as the growing demands arise from various kinds of AI applications.
Zhihong Xie +3 more
doaj +2 more sources
Filter Pruning Based on Information Capacity and Independence
IEEE Transactions on Neural Networks and Learning SystemsFilter pruning has gained widespread adoption for the purpose of compressing and speeding up convolutional neural networks (CNNs). However, existing approaches are still far from practical applications due to biased filter selection and heavy computation cost.
Yufeng Shi, , Qinmu Peng
exaly +4 more sources
Filter Sketch for Network Pruning [PDF]
IEEE Transactions on Neural Networks and Learning Systems, 2022 We propose a novel network pruning approach by information preserving of pre-trained network weights (filters). Network pruning with the information preserving is formulated as a matrix sketch problem, which is efficiently solved by the off-the-shelf Frequent Direction method.
Mingbao Lin +7 more
openaire +5 more sources
Efficient tensor decomposition-based filter pruning
Neural NetworksIn this paper, we present CORING, which is short for effiCient tensOr decomposition-based filteR prunING, a novel filter pruning methodology for neural networks. CORING is crafted to achieve efficient tensor decomposition-based pruning, a stark departure from conventional approaches that rely on vectorized or matricized filter representations.
Thanh Phuong Nguyen +2 more
exaly +4 more sources
To Filter Prune, or to Layer Prune, That Is the Question [PDF]
, 2021 Recent advances in pruning of neural networks have made it possible to remove a large number of filters or weights without any perceptible drop in accuracy. The number of parameters and that of FLOPs are usually the reported metrics to measure the quality of the pruned models.
Sara Elkerdawy +4 more
openaire +2 more sources
YOLO Pruning Algorithm Based on Parameter Subspace and Scaling Factor [PDF]
Jisuanji gongcheng, 2021 In order to ensure the normal operation of YOLO network on embedded devices,it is necessary to use pruning algorithm to simplify the filter to reduce the network storage space and the amount of calculation.
YANG Minjie, LIANG Yaling, DU Minghui
doaj +1 more source
Automated Filter Pruning Based on High-Dimensional Bayesian Optimization
IEEE Access, 2022 Filter pruning is necessary to efficiently deploy convolutional neural networks on edge devices that have limited computational resources and power budgets.
Taehyeon Kim +2 more
doaj +1 more source