TY - GEN
T1 - Computational Visual Ceramicology
T2 - 35th AAAI Conference on Artificial Intelligence, AAAI 2021
AU - Itkin, Barak
AU - Wolf, Lior
AU - Dershowitz, Nachum
N1 - Publisher Copyright:
© 2021, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.
PY - 2021
Y1 - 2021
N2 - Field archeologists are called upon to identify potsherds, for which they rely on their professional experience and on reference works. We have developed a recognition method starting from images captured on site, which relies on the shape of the sherd's fracture outline. The method sets up a new target for deep-learning, integrating information from points along inner and outer surfaces to learn about shapes. Training the classifiers required tackling multiple challenges that arose on account of our working with real-world archeological data: paucity of labeled data; extreme imbalance between instances of different categories; and the need to avoid neglecting rare classes and to take note of minute distinguishing features of some classes. The scarcity of training data was overcome by using synthetically-produced virtual potsherds and by employing multiple data-augmentation techniques. A novel form of training loss allowed us to overcome classification problems caused by under-populated classes and inhomogeneous distribution of discriminative features.
AB - Field archeologists are called upon to identify potsherds, for which they rely on their professional experience and on reference works. We have developed a recognition method starting from images captured on site, which relies on the shape of the sherd's fracture outline. The method sets up a new target for deep-learning, integrating information from points along inner and outer surfaces to learn about shapes. Training the classifiers required tackling multiple challenges that arose on account of our working with real-world archeological data: paucity of labeled data; extreme imbalance between instances of different categories; and the need to avoid neglecting rare classes and to take note of minute distinguishing features of some classes. The scarcity of training data was overcome by using synthetically-produced virtual potsherds and by employing multiple data-augmentation techniques. A novel form of training loss allowed us to overcome classification problems caused by under-populated classes and inhomogeneous distribution of discriminative features.
UR - http://www.scopus.com/inward/record.url?scp=85130095706&partnerID=8YFLogxK
U2 - 10.1609/aaai.v35i17.17740
DO - 10.1609/aaai.v35i17.17740
M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???
AN - SCOPUS:85130095706
T3 - 35th AAAI Conference on Artificial Intelligence, AAAI 2021
SP - 14822
EP - 14830
BT - 35th AAAI Conference on Artificial Intelligence, AAAI 2021
PB - Association for the Advancement of Artificial Intelligence
Y2 - 2 February 2021 through 9 February 2021
ER -