Convolutional Tables Ensemble: classification in microseconds

Autor:	Bar-Hillel, Aharon, Krupka, Eyal, Bloom, Noam
Rok vydání:	2016
Předmět:	Computer Science - Computer Vision and Pattern Recognition Computer Science - Learning 68T45
Druh dokumentu:	Working Paper
Popis:	We study classifiers operating under severe classification time constraints, corresponding to 1-1000 CPU microseconds, using Convolutional Tables Ensemble (CTE), an inherently fast architecture for object category recognition. The architecture is based on convolutionally-applied sparse feature extraction, using trees or ferns, and a linear voting layer. Several structure and optimization variants are considered, including novel decision functions, tree learning algorithm, and distillation from CNN to CTE architecture. Accuracy improvements of 24-45% over related art of similar speed are demonstrated on standard object recognition benchmarks. Using Pareto speed-accuracy curves, we show that CTE can provide better accuracy than Convolutional Neural Networks (CNN) for a certain range of classification time constraints, or alternatively provide similar error rates with 5-200X speedup. Comment: 10 pages
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1602.04489 Zobrazit plný text záznamu View this record from Arxiv