One Shot Learning via Compositions of Meaningful Patches CCVL Alex Wong Alan L. Yuille University of California, Los Angeles http://ccvl.stat.ucla.edu/ Current stateoftheart algorithms perform very well on most common datasets when trained on thousands of examples However, humans are able to learn a concept from very few examples, perhaps even just one mo8va8on One shot learning is an object categoriza@on task where very few examples (15) are given for training what is one shot learning? • Learn a meaningful patchbased representa@on of the underlying structure of an object without human supervision • Build a composi@onal model composed of a set of compact dic@onaries of meaningful patches • Reconstruct the target image with deforma@ons of the meaningful patch dic@onaries by patch matching • Select the class of the best proposed reconstruc@on as label our approach Training Images Segmented Images into Parts (Features) Compositional Model Test Image Reconstruction Select Best Fit Parts Representing Each Region Dictionaries of Deformed Parts • Our composi@onal model outperforms popular algorithms on the recogni@on task under one shot learning • The extracted features are seman@cally meaningful • The model generalizes beyond the training set and demonstrates transferability between separate datasets conclusion experimental results • Symmetry axis acts as a robust object descriptor • Branch points separate one meaningful part from another • Small segments are merged with nearby meaningful parts feature extrac8on • Similar parts, defined by a high match score via Normalized Cross Correla@on, are merged to create a compact dic@onary • An ANDOR graph of the part rela@ons is construc@on for m patches for samples t and u: • Deforma@ons are applied to the meaningful patches composi8onal model We would like to thank Brian Taylor for performing experiments and edi@ng the manuscript. This work was supported by NSF STC award CCF1231216 and ONR N000141210883. acknowledgements sample reconstruc8ons truth=1 label=2 label=6 truth=1 truth=2 label=7 truth=2 label=4 truth=3 label=2 truth=3 label=5 truth=4 label=9 truth=4 label=9 truth=5 label=4 truth=5 label=3 truth=6 label=4 truth=6 label=5 truth=7 label=3 truth=7 label=2 truth=8 label=6 truth=8 label=2 truth=9 label=8 truth=9 label=4 truth=0 label=3 truth=0 label=9 MNIST USPS (trained on MNIST) Images in the Wild (trained on MNIST) Misclassifications *left image denotes test image, right image denotes reconstruction