Is Object Localization for Free? - Weakly-Supervised Learning With Convolutional Neural Networks

Maxime Oquab, Leon Bottou, Ivan Laptev, Josef Sivic; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 685-694

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.

Related Material


[pdf]
[bibtex]
@InProceedings{Oquab_2015_CVPR,
author = {Oquab, Maxime and Bottou, Leon and Laptev, Ivan and Sivic, Josef},
title = {Is Object Localization for Free? - Weakly-Supervised Learning With Convolutional Neural Networks},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2015}
}