A Framework of Transfer Learning in Object Detection for Embedded Systems
arXiv:1811.04863
Abstract
Transfer learning is one of the subjects undergoing intense study in the area of machine learning. In object recognition and object detection there are known experiments for the transferability of parameters, but not for neural networks which are suitable for object detection in real time embedded applications, such as the SqueezeDet neural network. We use transfer learning to accelerate the training of SqueezeDet to a new group of classes. Also, experiments are conducted to study the transferability and co-adaptation phenomena introduced by the transfer learning process. To accelerate training, we propose a new implementation of the SqueezeDet training which provides a faster pipeline for data processing and achieves 1.8 times speedup compared to the initial implementation. Finally, we created a mechanism for automatic hyperparameter optimization using an empirical method.
References in corpus (8)
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- Overcoming catastrophic forgetting in neural networks
- SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
- YOLO9000: Better, Faster, Stronger
- Speed/accuracy trade-offs for modern convolutional object detectors
- BOCK : Bayesian Optimization with Cylindrical Kernels
- Global optimization of Lipschitz functions
- Fast and Energy-Efficient CNN Inference on IoT Devices