Title | ||
---|---|---|
PProCRC: Probabilistic Collaboration of Image Patches for Fine-grained Classification |
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). |
Year | DOI | Venue |
---|---|---|
2020 | 10.1109/IVCNZ51579.2020.9290537 | 2020 35th International Conference on Image and Vision Computing New Zealand (IVCNZ) |
Keywords | DocType | ISSN |
Fine-grained visual categorization (FGVC),collaborative representation classifiers (CRC),species recognition | Conference | 2151-2191 |
ISBN | Citations | PageRank |
978-1-7281-8580-4 | 0 | 0.34 |
References | Authors | |
0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Tapabrata Chakraborti | 1 | 18 | 5.06 |
brendan mccane | 2 | 223 | 33.05 |
Steven Mills | 3 | 186 | 18.39 |
Umapada Pal | 4 | 1477 | 139.32 |