ActNAS : Generating Efficient YOLO Models using Activation NAS
This work addresses efficiency improvements for YOLO models on edge devices, but it is incremental as it builds on existing NAS and activation function techniques.
The paper tackled the problem of optimizing activation functions in YOLO models for edge devices by proposing a Neural Architecture Search (NAS) method to design models with mixed activation functions, resulting in a model that is 22.28% faster and uses 64.15% less memory on an NPU with a slight mAP improvement.
Activation functions introduce non-linearity into Neural Networks, enabling them to learn complex patterns. Different activation functions vary in speed and accuracy, ranging from faster but less accurate options like ReLU to slower but more accurate functions like SiLU or SELU. Typically, same activation function is used throughout an entire model architecture. In this paper, we conduct a comprehensive study on the effects of using mixed activation functions in YOLO-based models, evaluating their impact on latency, memory usage, and accuracy across CPU, NPU, and GPU edge devices. We also propose a novel approach that leverages Neural Architecture Search (NAS) to design YOLO models with optimized mixed activation functions.The best model generated through this method demonstrates a slight improvement in mean Average Precision (mAP) compared to baseline model (SiLU), while it is 22.28% faster and consumes 64.15% less memory on the reference NPU device.