On Generalizing Detection Models for Unconstrained Environments

ICCVW 2019 pp. 4296-4301

doi:10.1109/ICCVW.2019.00529 /iccvw/2019/bhargava2019iccvw-generalizing/

Abstract

Object detection has seen tremendous progress in recent years. However, current algorithms don't generalize well when tested on diverse data distributions. We address the problem of incremental learning in object detection on the India Driving Dataset (IDD). Our approach involves using multiple domain-specific classifiers and effective transfer learning techniques focussed on avoiding catastrophic forgetting. We evaluate our approach on the IDD and BDD100K dataset. Results show the effectiveness of our domain adaptive approach in the case of domain shifts in environments.

PDF ICCVW Semantic Scholar

Cite

Text

Bhargava. "On Generalizing Detection Models for Unconstrained Environments." IEEE/CVF International Conference on Computer Vision Workshops, 2019. doi:10.1109/ICCVW.2019.00529

Markdown

[Bhargava. "On Generalizing Detection Models for Unconstrained Environments." IEEE/CVF International Conference on Computer Vision Workshops, 2019.](https://mlanthology.org/iccvw/2019/bhargava2019iccvw-generalizing/) doi:10.1109/ICCVW.2019.00529

BibTeX

@inproceedings{bhargava2019iccvw-generalizing,
  title     = {{On Generalizing Detection Models for Unconstrained Environments}},
  author    = {Bhargava, Prajjwal},
  booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
  year      = {2019},
  pages     = {4296-4301},
  doi       = {10.1109/ICCVW.2019.00529},
  url       = {https://mlanthology.org/iccvw/2019/bhargava2019iccvw-generalizing/}
}