Answers are grounded in this paper and cite their sources.
• The basic conditions to build the agent were determined. • The operation conditions to drive the agent were determined with improved transfer learning. • The agent was used to auto-optimize the pre-trained network. Deep learning networks have been widely used for vegetation detection in field images to monitor environmental information, but a network optimized by manual methods requires extensive experience and T&E (trial and error). So, this paper proposed an agent to auto-optimize networks using a Directed Evolutionary Genetic Algorithm (DEGA) and an auto transfer learning method (FMTPI) for vegetation detection in dry thermal valley. Firstly, the basic conditions to build the agent were determined, showing that the optimal basic conditions were Resnet type with an input size of 753, a block depth of 4, and a kernel size of 3. Secondly, the operation conditions to drive the agent were obtained with the improved FMTPI, showing that the exponential + the inverse fitting FMTPI can reduce the time of 90.1%. Finally, the agent auto-optimized the pre-trained network, showing that the model size could be reduced by 87.3% while maintaining an accuracy of 92.3%. The agent can auto-optimize networks and improve network efficiency, provided a meaningful reference for vegetation or environment detection.
No takes yet. Share an insight, caveat, or question.
Chen et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: