Back to Search Start Over

PProCRC: Probabilistic Collaboration of Image Patches

Authors :
Chakraborti, Tapabrata
McCane, Brendan
Mills, Steven
Pal, Umapada
Publication Year :
2019

Abstract

We present a conditional probabilistic framework for collaborative representation of image patches. It incorporates background compensation and outlier patch suppression into the main formulation itself, thus doing away with the need for pre-processing steps to handle the same. A closed form non-iterative solution of the cost function is derived. The proposed method (PProCRC) outperforms earlier CRC formulations: patch based (PCRC, GP-CRC) as well as the state-of-the-art probabilistic (ProCRC and EProCRC) on three fine-grained species recognition datasets (Oxford Flowers, Oxford-IIIT Pets and CUB Birds) using two CNN backbones (Vgg-19 and ResNet-50).

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.1903.09123
Document Type :
Working Paper