Three-Dimensional Convolutional Neural Network Pruning with Regularization-Based Method
Yuxin Zhang,Huan Wang,Yang Luo,Lu Yu,Haoji Hu,Hangguan Shan,Tony Q. S. Quek +6 more
- 01 Sep 2019
- pp 4270-4274
TL;DR: A three-dimensional regularization-based neural network pruning method to assign different regularization parameters to different weight groups based on their importance to the network based on the redundancy and computation cost for each layer.
read more
Abstract: Despite enjoying extensive applications in video analysis, three-dimensional convolutional neural networks (3D CNNs) are restricted by their massive computation and storage consumption. To solve this problem, we propose a three-dimensional regularization-based neural network pruning method to assign different regularization parameters to different weight groups based on their importance to the network. Further we analyze the redundancy and computation cost for each layer to determine the different pruning ratios. Experiments show that pruning based on our method can lead to 2× theoretical speedup with only 0.41% accuracy loss for 3D-ResNet18 and 3.28% accuracy loss for C3D. The proposed method performs favorably against other popular methods for model compression and acceleration.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Multi-Dimensional Pruning: A Unified Framework for Model Compression
Jinyang Guo,Wanli Ouyang,Dong Xu +2 more
- 14 Jun 2020
TL;DR: This work proposes a unified model compression framework called Multi-Dimensional Pruning (MDP) to simultaneously compress the convolutional neural networks (CNNs) on multiple dimensions and demonstrates that the MDP framework outperforms the existing methods when pruning both 2D and 3D CNNs.
Channel Pruning Guided by Classification Loss and Feature Importance
Jinyang Guo,Wanli Ouyang,Dong Xu +2 more
- 03 Apr 2020
TL;DR: This work proposes a new layer-by-layer channel pruning method called Channel Pruning guided by classification Loss and feature Importance (CPLI), which additionally take the classification loss into account in the channel pruned process.
Frequency Domain Compact 3D Convolutional Neural Networks
Hanting Chen,Yunhe Wang,Han Shu,Yehui Tang,Chunjing Xu,Boxin Shi,Chao Xu,Qi Tian,Chang Xu +8 more
- 14 Jun 2020
TL;DR: A novel approach for eliminating redundancy in the time dimensionality of 3D convolution filters by converting them into the frequency domain through a series of learned optimal transforms with extremely fewer parameters is developed.
•Posted Content
Channel Pruning Guided by Classification Loss and Feature Importance
Jinyang Guo,Wanli Ouyang,Dong Xu +2 more
TL;DR: In this article, a new layer-by-layer channel pruning method called Channel Pruning guided by classification Loss and feature Importance (CPLI) is proposed to suppress the influence of unimportant features (i.e., the features will be removed at the next pruning stage).
5
KG-Planner: Knowledge-Informed Graph Neural Planning for Collaborative Manipulators
Wansong Liu,Kareem Eltouny,Sibo Tian,Xiao Liang,Minghui Zheng +4 more
- 13 May 2024
TL;DR: KG-Planner is a novel knowledge-informed graph neural planner for collaborative manipulators that efficiently plans collision-free motions in high-dimensional spaces. It incorporates physical knowledge from the workspace to generate nearly optimal robot motions.
References
•Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
- 04 Sep 2014
TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
102.6K
Going deeper with convolutions
Christian Szegedy,Wei Liu,Yangqing Jia,Pierre Sermanet,Scott Reed,Dragomir Anguelov,Dumitru Erhan,Vincent Vanhoucke,Andrew Rabinovich +8 more
- 07 Jun 2015
TL;DR: Inception as mentioned in this paper is a deep convolutional neural network architecture that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14).
•Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
- 01 Jan 2015
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
51.9K
You Only Look Once: Unified, Real-Time Object Detection
Joseph Redmon,Santosh K. Divvala,Ross Girshick,Ali Farhadi +3 more
- 27 Jun 2016
TL;DR: Compared to state-of-the-art detection systems, YOLO makes more localization errors but is less likely to predict false positives on background, and outperforms other detection methods, including DPM and R-CNN, when generalizing from natural images to other domains like artwork.
Fast R-CNN
Ross Girshick
- 07 Dec 2015
TL;DR: Fast R-CNN as discussed by the authors proposes a Fast Region-based Convolutional Network method for object detection, which employs several innovations to improve training and testing speed while also increasing detection accuracy and achieves a higher mAP on PASCAL VOC 2012.