Is object localization for free? – Weakly-supervised learning with convolutional neural networks - Archive ouverte HAL Access content directly
Conference Papers Year :

Is object localization for free? – Weakly-supervised learning with convolutional neural networks

(1, 2, 3) , (4) , (2, 3) , (2, 3)
1
2
3
4

Abstract

Successful methods for visual object recognition typically rely on training datasets containing lots of richly annotated images. Detailed image annotation, e.g. by object bounding boxes, however, is both expensive and often 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 comparably to its fully-supervised counterparts using object bounding box annotation for training.
Fichier principal
Vignette du fichier
Oquab15.pdf (1.74 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01015140 , version 1 (25-06-2014)
hal-01015140 , version 2 (17-05-2015)

Identifiers

  • HAL Id : hal-01015140 , version 2

Cite

Maxime Oquab, Léon Bottou, Ivan Laptev, Josef Sivic. Is object localization for free? – Weakly-supervised learning with convolutional neural networks. IEEE Conference on Computer Vision and Pattern Recognition, Jun 2015, Boston, United States. ⟨hal-01015140v2⟩
2725 View
8809 Download

Share

Gmail Facebook Twitter LinkedIn More