Deep Learning Architecture Improvement Based on Dynamic Pruning and Layer Fusion

Abstract

The heavy workload of current deep learning architectures significantly impedes the application of deep learning, especially on resource-constrained devices. Pruning has provided a promising solution to compressing the bloated deep learning models by removing the redundancies of the networks. However, existing pruning methods mainly focus on compressing the superfluous channels without considering layer-level redundancies, which results in the channel-pruned models still suffering from serious redundancies. To mitigate this problem, we propose an effective compression algorithm for deep learning models that uses both the channel-level and layer-level compression techniques to optimize the enormous deep learning models. In detail, the channels are dynamically pruned first, and then the model is further optimized by fusing the redundant layers. Only a minor performance loss results. The experimental results show that the computations of ResNet-110 are reduced by 80.05%, yet the accuracy is only decreased by 0.72%. Forty-eight convolutional layers could be discarded from ResNet-110 with no loss of performance, which fully demonstrates the efficiency of the proposal.

Real-Time Object Detection and Tracking for Unmanned Aerial Vehicles Based on Convolutional Neural Networks

“…Pruning methods have been proposed to reduce the complexity of CNN models [13][14][15][16][17]. Channel pruning intends to exploit the redundancy of feature maps between channels and remove channels with the minimal performance loss [13].…”

“…Channel pruning intends to exploit the redundancy of feature maps between channels and remove channels with the minimal performance loss [13]. Li et al [14] proposed pruning deep learning models using both channel-level and layer-level compression techniques. Liu et al [16] designed a pruning method that can be directly applied to existing modern CNN architectures by enforcing channel-level sparsity in the network to reduce the model size, decrease the run-time memory footprint and lower the number of computing operations while maintaining the accuracy of the model.…”