Weakly supervised object localization with deep convolutional neural network based on spatial pyramid saliency map

Document Type

Conference Proceeding

Date of Original Version



Supervised object localization requires detailed image annotation, such as bounding box, to indicate the location of the object. However, labeling image with bounding box is labor-intensive. Besides, the labeling process may involve ambiguous decisions. Weakly supervised object localization only needs category annotation which is available in large amounts. Recently, many weakly supervised object localization methods, based on global pooling, have been proposed. However, these methods only localize part of the object. This paper proposes a deep convolutional neural network with spatial pyramid saliency map to localize the full extent of the object. The experimental result on Cub-200 dataset shows that our method outperforms the traditional ones.

Publication Title, e.g., Journal

Proceedings - International Conference on Image Processing, ICIP