MobilePrune: Neural Network Compression via ℓ0 Sparse Group Lasso on the Mobile System

Shao, Yubo; Zhao, Kun; Cao, Zhiwen; Peng, Zhehao; Peng, Xingang; Li, Pan; Wang, Yijie; Ma, Jianzhu

doi:10.3390/s22114081

Cited by 3 publications

(3 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…If the terrain condition is not considered, the detected road might be risky for UGV. Additionally, the inference speed of our method needs further improvement, and we will accelerate and prune the model to improve the inference speed [36].…”

Section: Discussionmentioning

confidence: 99%

ARDformer: Agroforestry Road Detection for Autonomous Driving Using Hierarchical Transformer

Firkat

Zhang

et al. 2022

Sensors

View full text Add to dashboard Cite

Road detection is a crucial part of the autonomous driving system, and semantic segmentation is used as the default method for this kind of task. However, the descriptive categories of agroforestry are not directly definable and constrain the semantic segmentation-based method for road detection. This paper proposes a novel road detection approach to overcome the problem mentioned above. Specifically, a novel two-stage method for road detection in an agroforestry environment, namely ARDformer. First, a transformer-based hierarchical feature aggregation network is used for semantic segmentation. After the segmentation network generates the scene mask, the edge extraction algorithm extracts the trail’s edge. It then calculates the periphery of the trail to surround the area where the trail and grass are located. The proposed method is tested on the public agroforestry dataset, and experimental results show that the intersection over union is approximately 0.82, which significantly outperforms the baseline. Moreover, ARDformer is also effective in a real agroforestry environment.

show abstract

Section: Discussionmentioning

confidence: 99%

ARDformer: Agroforestry Road Detection for Autonomous Driving Using Hierarchical Transformer

Firkat

Zhang

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…However, model deployment is sometimes costly due to the large number of parameters in the DNN. To address this problem, many methods [ 1 , 2 , 3 , 4 , 5 , 6 ] have been proposed to compress networks and reduce computational quantities. These methods are mainly divided into two categories: structured pruning and unstructured pruning, in which the main method of structured pruning is the filter pruning, while the unstructured pruning method is mainly achieved by weight pruning.…”

Section: Introductionmentioning

confidence: 99%

A Novel Deep-Learning Model Compression Based on Filter-Stripe Group Pruning and Its IoT Application

Zhao

Tong

et al. 2022

Sensors

View full text Add to dashboard Cite

Nowadays, there is a tradeoff between the deep-learning module-compression ratio and the module accuracy. In this paper, a strategy for refining the pruning quantification and weights based on neural network filters is proposed. Firstly, filters in the neural network were refined into strip-like filter strips. Then, the evaluation of the filter strips was used to refine the partial importance of the filter, cut off the unimportant filter strips and reorganize the remaining filter strips. Finally, the training of the neural network after recombination was quantified to further compress the computational amount of the neural network. The results show that the method can significantly reduce the computational effort of the neural network and compress the number of parameters in the model. Based on experimental results on ResNet56, this method can reduce the number of parameters to 1/4 and the amount of calculation to 1/5, and the loss of model accuracy is only 0.01. On VGG16, the number of parameters is reduced to 1/14, the amount of calculation is reduced to 1/3, and the accuracy loss is 0.5%.

show abstract

“…Convolutional Neural Networks (CNNs), a type of deep learning model, have demonstrated remarkable success in various computer vision tasks, including image classification, object detection, and segmentation [3]. Nevertheless, these models are often large and demand substantial computational resources for training and inference, which may hinder their deployment on resource-constrained devices like mobile phones and embedded systems [4].…”

mentioning

confidence: 99%

UNet++ Compression Techniques for Kidney and Cyst Segmentation in Autosomal Dominant Polycystic Kidney Disease

KRISHNAN,

SCHMIDT,

ONUOHA

et al. 2024

ABE

View full text Add to dashboard Cite

Autosomal Dominant Polycystic Kidney Disease (ADP-KD) is characterized by uncontrolled growth of renal cysts, resulting in variations in kidney volume. Therefore, the accurate quantification of kidney and cyst volume variation becomes crucial for monitoring treatment response [1]. Manual segmentation is laborious and time-consuming, with limited reproducibility, thus deep learning-based algorithms have gained popularity for automating the segmentation process with improved accuracy [2].

show abstract

MobilePrune: Neural Network Compression via ℓ0 Sparse Group Lasso on the Mobile System

Cited by 3 publications

References 27 publications

ARDformer: Agroforestry Road Detection for Autonomous Driving Using Hierarchical Transformer

ARDformer: Agroforestry Road Detection for Autonomous Driving Using Hierarchical Transformer

A Novel Deep-Learning Model Compression Based on Filter-Stripe Group Pruning and Its IoT Application

UNet++ Compression Techniques for Kidney and Cyst Segmentation in Autosomal Dominant Polycystic Kidney Disease

Contact Info

Product

Resources

About