@InProceedings{PetscharnigME17, author = {Petscharnig, Stefan and Schoeffmann, Klaus and Lux, Mathias}, booktitle = {Working Notes Proceedings of the MediaEval 2017 Workshop}, title = {An Inception-like CNN Architecture for GI Disease and Anatomical Landmark Classification}, year = {2017}, address = {Vol-1984}, editor = {Gravier, Guillaume and Bischke, Benjamin and Demarty, Claire-Hélène and Zaharieva, Maia and Riegler, Michael and Dellandrea, Emmanuel and Bogdanov, Dmitry and Sutcliffe, Richard and Jones, Gareth and Larson, Martha}, month = {oct}, pages = {1--3}, publisher = {CEUR-WS}, abstract = {In this working note, we describe our approach to gastrointestinal disease and anatomical landmark classification for the Medico task at MediaEval 2017. We propose an inception-like CNN architecture and a fixed-crop data augmentation scheme for training and testing. The architecture is based on GoogLeNet and designed to keep the number of trainable parameters and its computational overhead small. Preliminary experiments show that the architecture is able to learn the classification problem from scratch using a tiny fraction of the provided training data only.}, language = {EN}, location = {Dublin, Ireland}, talkdate = {2017.09.15}, talktype = {registered}, url = {http://slim-sig.irisa.fr/me17/} }