Fast, Accurate Detection of 100,000 Object Classes on a Single Machine: Technical Supplement
Venue
Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, IEEE Computer Society, Washington, DC, USA (2013)
Publication Year
2013
Authors
Thomas Dean, Mark Ruzon, Mark Segal, Jonathon Shlens, Sudheendra Vijayanarasimhan, Jay Yagnik
BibTeX
Abstract
It is possible to train DPM models not on HOG data but on a hashed WTA [Yagnik et al ICCV 2011] version of this data. The resulting part filters are sparse, real-valued vectors the size of WTA vectors computed from sliding windows. Given the WTA hash of a window, we exactly recover dot products of the top responses using an extension of locality-sensitive hashing. In this supplement, we sketch a method for training such WTA-based models.
