BROWSE
Detail
Conference Paper
Selective Inference for Accelerating Deep Learning-based Image Classification
Cited 5 time in 
Share 
Share
- Authors
- HyunYong Lee, Byung-Tak Lee
- Issue Date
- 2016-10
- Citation
- International Conference on Information and Communication Technology Convergence (ICTC) 2016, pp.135-137
- Publisher
- IEEE
- Language
- English
- Type
- Conference Paper
- Abstract
- Reducing the computational budget of inference in deep neural network while achieving high accuracy is important for time-sensitive applications. In this paper, unlike other approaches that try to compress a large neural network to a neural network with a smaller number of parameters, we try to complete the image classification as early as possible. Adding a middle output layer, we try to complete the image classification at the middle output layer when Top1 confidence exceeds a predefined confidence threshold. We prove the feasibility of proposed approach based on experiment using Inception-v3 in TensorFlow.
- KSP Keywords
- Confidence threshold, Deep neural network(DNN), High accuracy, Image Classification, Inception-v3, Learning-based, Output layer, Selective inference, Time-sensitive, deep learning(DL), neural network(NN)