Elastic Neural Networks: A Scalable Framework for Embedded Computer Vision
Tutkimustuotos › › vertaisarvioitu
Yksityiskohdat
Alkuperäiskieli | Englanti |
---|---|
Otsikko | 2018 26th European Signal Processing Conference (EUSIPCO) |
Kustantaja | IEEE |
ISBN (elektroninen) | 978-9-0827-9701-5 |
ISBN (painettu) | 978-1-5386-3736-4 |
DOI - pysyväislinkit | |
Tila | Julkaistu - syyskuuta 2018 |
OKM-julkaisutyyppi | A4 Artikkeli konferenssijulkaisussa |
Tapahtuma | EUROPEAN SIGNAL PROCESSING CONFERENCE - Kesto: 1 tammikuuta 1900 → … |
Julkaisusarja
Nimi | |
---|---|
ISSN (elektroninen) | 2076-1465 |
Conference
Conference | EUROPEAN SIGNAL PROCESSING CONFERENCE |
---|---|
Ajanjakso | 1/01/00 → … |
Tiivistelmä
We propose a new framework for image classification with deep neural networks. The framework introduces intermediate outputs to the computational graph of a network. This enables flexible control of the computational load and balances the tradeoff between accuracy and execution time. Moreover, we present an interesting finding that the intermediate outputs can act as a regularizer at training time, improving the prediction accuracy. In the experimental section we demonstrate the performance of our proposed framework with various commonly used pretrained deep networks in the use case of apparent age estimation.