Is Object Localization for Free? - Weakly-Supervised Learning with Convolutional Neural Networks
Abstract
Successful visual object recognition methods typically rely on training datasets containing lots of richly annotated images. Annotating object bounding boxes is both expensive and subjective. We describe a weakly supervised convolutional neural network (CNN) for object classification that relies only on image-level labels, yet can learn from cluttered scenes containing multiple objects. We quantify its object classification and object location prediction performance on the Pascal VOC 2012 (20 object classes) and the much larger Microsoft COCO (80 object classes) datasets. We find that the network (i) outputs accurate image-level labels, (ii) predicts approximate locations (but not extents) of objects, and (iii) performs similar or better compared to its fully-supervised counterparts using object bounding box annotation for training.
Cite
Text
Oquab et al. "Is Object Localization for Free? - Weakly-Supervised Learning with Convolutional Neural Networks." Conference on Computer Vision and Pattern Recognition, 2015. doi:10.1109/CVPR.2015.7298668Markdown
[Oquab et al. "Is Object Localization for Free? - Weakly-Supervised Learning with Convolutional Neural Networks." Conference on Computer Vision and Pattern Recognition, 2015.](https://mlanthology.org/cvpr/2015/oquab2015cvpr-object/) doi:10.1109/CVPR.2015.7298668BibTeX
@inproceedings{oquab2015cvpr-object,
title = {{Is Object Localization for Free? - Weakly-Supervised Learning with Convolutional Neural Networks}},
author = {Oquab, Maxime and Bottou, Leon and Laptev, Ivan and Sivic, Josef},
booktitle = {Conference on Computer Vision and Pattern Recognition},
year = {2015},
doi = {10.1109/CVPR.2015.7298668},
url = {https://mlanthology.org/cvpr/2015/oquab2015cvpr-object/}
}