Towards Fine-Grained Sampling for Active Learning in Object Detection
Abstract
We study the problem of using active learning to reduce annotation effort in training object detectors. Existing efforts in this space ignore the fact that image annotation costs are variable, depending on the number of objects present in a single image. In this regard, we examine a fine-grained sampling based approach for active learning in object detection. Over an unlabeled pool of images, our method aims to selectively pick the most informative subset of bounding boxes (as opposed to full images) to query an annotator. We measure annotation efforts in terms of the number of ground truth bounding boxes obtained. We study the effects of our method on the Feature Pyramid Network and RetinaNet models, and show promising savings in labeling effort to obtain good detection performance.
Cite
Text
Desai and Balasubramanian. "Towards Fine-Grained Sampling for Active Learning in Object Detection." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020. doi:10.1109/CVPRW50498.2020.00470Markdown
[Desai and Balasubramanian. "Towards Fine-Grained Sampling for Active Learning in Object Detection." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020.](https://mlanthology.org/cvprw/2020/desai2020cvprw-finegrained/) doi:10.1109/CVPRW50498.2020.00470BibTeX
@inproceedings{desai2020cvprw-finegrained,
title = {{Towards Fine-Grained Sampling for Active Learning in Object Detection}},
author = {Desai, Sai Vikas and Balasubramanian, Vineeth N.},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2020},
pages = {4010-4014},
doi = {10.1109/CVPRW50498.2020.00470},
url = {https://mlanthology.org/cvprw/2020/desai2020cvprw-finegrained/}
}