Weakly supervised learning of object detection is an important problem in image understanding that still does not have a satisfactory solution. In this paper, we address this problem by exploiting the power of deep convolutional neural networks pre-trained on large-scale image-level classification tasks. We propose a weakly supervised deep detection architecture that modifies one such network to operate at the level of image regions, performing simultaneously region selection and classification. Trained as an image classifier, the architecture implicitly learns object detectors that are better than alternative weakly supervised detection systems on the PASCAL VOC data. The model, which is a simple and elegant end-to-end architecture, outperforms standard data augmentation and fine-tuning techniques for the task of image-level classification as well.

9 pages, 3 figures, 6 tables, Conference on Computer Vision and Pattern Recognition (CVPR) 2016. This version fixes the equation in Section 3.4, thanks to Vadim Kantorov and Sini\v{s}a \v{S}egvi\'c