Search papers, labs, and topics across Lattice.
The paper introduces WPMNet, a lightweight CNN architecture for interference recognition that directly processes raw time-series data. To reduce computational cost, the authors employ an adaptive search algorithm to determine the optimal pruning threshold for weight pruning, followed by parameter quantization. Experiments show that WPMNet achieves a compression ratio of 84.5% with only a slight decrease in average recognition accuracy from 97.6% to 95.08%.
You can slash your interference recognition model size by 84% with minimal accuracy loss using this pruning and quantization aware multi-scale CNN.
Interference recognition serves as the preprocessing technology for interference suppression. Researchers typically employ the method based on the time-frequency graph - deep convolutional neural network (CNN) in pursuit of recognition accuracy. Nevertheless, certain time-frequency analysis processing approaches or network models with excessive parameters make it challenging to apply this technology to devices with limited resources. In this paper, a weight pruning and parameter quantization assisted multi-Scale lightweight network named WPMNet is proposed, which can directly take the raw time series data as input. The network model comprises three multi-scale convolutional modules, an attention mechanism, and fully connected layers. The multi-scale convolutional modules are composed of convolutional kernels of different sizes in parallel, aiming to extract deep-level features and features of various granularities simultaneously. To compress the model, we introduce an adaptive search algorithm for determining the optimal pruning threshold for weight pruning, ensuring that the accuracy decline is within an acceptable range. And the model is further compressed through parameter quantization. The experimental outcomes demonstrate that prior to the lightweighting of the model, the average recognition accuracy was 97.6%. After the lightweight processing, the compression ratio of the network attained 84.5%, while the average recognition accuracy merely declined slightly to 95.08%. This substantiates that the proposed approach is applicable to scenarios that simultaneously demand both high precision and model deployability, such as embedded systems or mobile devices.
