Three Dimensional Convolutional Neural Network Pruning with Regularization-Based Method
원문 초록
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 threedimensional 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 2x theoretical speedup with only 0.41% accuracy loss for 3DResNet18 and 3.28% accuracy loss for C3D. The proposed method performs favorably against other popular methods for model compression and acceleration.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Boosting Large Language Models with Mask Fine-Tuning
Neural Architecture Codesign for Fast Physics Applications
MaskLLM: Learnable Semi-Structured Sparsity for Large Language Models
Aggressive Post-Training Compression on Extremely Large Language Models
Comprehensive Study on Performance Evaluation and Optimization of Model Compression: Bridging Traditional Deep Learning and Large Language Models
Simple is what you need for efficient and accurate medical image segmentation
토론
이 논문과 연결된 포럼 글이 아직 없습니다.