Incremental Learning in Person Re-Identification

Published in CoRR, 2018

Abstract

Person Re-Identification is still a challenging task in Computer Vision due to a variety of reasons. On the other side, Incremental Learning is still an issue since deep learning models tend to face the problem of over catastrophic forgetting when trained on subsequent tasks. In this paper, we propose a model that can be used for multiple tasks in Person Re-Identification, provide state-of-the-art results on a variety of tasks and still achieve considerable accuracy subsequently. We evaluated our model on two datasets Market 1501 and Duke MTMC. Extensive experiments show that this method can achieve Incremental Learning in Person ReID efficiently as well as for other tasks in computer vision as well.

Paper can be found on arXiv Code can be found on Github

To cite, please use the following Bibtex

@article{DBLP:journals/corr/abs-1808-06281,
  author    = {Prajjwal Bhargava},
  title     = {Incremental Learning in Person Re-Identification},
  journal   = {CoRR},
  volume    = {abs/1808.06281},
  year      = {2018},
  url       = {http://arxiv.org/abs/1808.06281},
  archivePrefix = {arXiv},
  eprint    = {1808.06281},
  timestamp = {Sun, 02 Sep 2018 15:01:56 +0200},
  biburl    = {https://dblp.org/rec/bib/journals/corr/abs-1808-06281},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}