Image Processing Method and Apparatus Based on Adversarial Neural Network Architecture Search
By introducing network vulnerability constraints into the DNN network structure search, the network structure is optimized, which solves the problem of DNN's vulnerability to adversarial sample attacks and improves the network's adversarial robustness and image processing accuracy.
CN116304144BActive Publication Date: 2026-05-26HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO LTD
View PDF 3 Cites 0 Cited by
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO LTD
- Filing Date
- 2022-12-27
- Publication Date
- 2026-05-26
Smart Images
Figure CN116304144B_ABST
Abstract
This application provides an image processing method and apparatus based on adversarial neural network (DNN) architecture search. The method includes: for any epoch in the DNN architecture search process, iteratively updating the operating parameters and structural parameters of the DNN network using a gradient descent algorithm, an acquired image training set, and an acquired image validation set until the number of iterations reaches a first iteration number; and iteratively updating the structural parameters of the DNN network using preset network vulnerability constraints and the acquired image validation set until the number of iterations within that epoch reaches a second iteration number; when the number of searched epochs reaches the first epoch number, or when the DNN network model converges, generating a target DNN network for image processing based on the obtained structural parameters, and using the target DNN network to process the image to be processed. This method can improve the accuracy of image processing using DNN networks.
Need to check novelty before this filing date? Find Prior Art