한국방송∙미디어공학회:학술대회논문집 (Proceedings of the Korean Society of Broadcast Engineers Conference)
- 한국방송∙미디어공학회 2018년도 추계학술대회
- /
- Pages.11-14
- /
- 2018
Correcting Misclassified Image Features with Convolutional Coding
- Mun, Ye-Ji (Department of Electronic and Electrical Engineering, Ewha W. University) ;
- Kim, Nayoung (Department of Electronic and Electrical Engineering, Ewha W. University) ;
- Lee, Jieun (Department of Electronic and Electrical Engineering, Ewha W. University) ;
- Kang, Je-Won (Department of Electronic and Electrical Engineering, Ewha W. University)
- 발행 : 2018.11.02
초록
The aim of this study is to rectify the misclassified image features and enhance the performance of image classification tasks by incorporating a channel- coding technique, widely used in telecommunication. Specifically, the proposed algorithm employs the error - correcting mechanism of convolutional coding combined with the convolutional neural networks (CNNs) that are the state - of- the- arts image classifier s. We develop an encoder and a decoder to employ the error - correcting capability of the convolutional coding. In the encoder, the label values of the image data are converted to convolutional codes that are used as target outputs of the CNN, and the network is trained to minimize the Euclidean distance between the target output codes and the actual output codes. In order to correct misclassified features, the outputs of the network are decoded through the trellis structure with Viterbi algorithm before determining the final prediction. This paper demonstrates that the proposed architecture advances the performance of the neural networks compared to the traditional one- hot encoding method.
키워드