DocumentCode :
3748728
Title :
DeepProposal: Hunting Objects by Cascading Deep Convolutional Layers
Author :
Amir Ghodrati;Ali Diba;Marco Pedersoli;Tinne Tuytelaars;Luc Van Gool
Author_Institution :
ESAT-PSI, KU Leuven, Leuven, Belgium
fYear :
2015
Firstpage :
2578
Lastpage :
2586
Abstract :
In this paper we evaluate the quality of the activation layers of a convolutional neural network (CNN) for the generation of object proposals. We generate hypotheses in a sliding-window fashion over different activation layers and show that the final convolutional layers can find the object of interest with high recall but poor localization due to the coarseness of the feature maps. Instead, the first layers of the network can better localize the object of interest but with a reduced recall. Based on this observation we design a method for proposing object locations that is based on CNN features and that combines the best of both worlds. We build an inverse cascade that, going from the final to the initial convolutional layers of the CNN, selects the most promising object locations and refines their boxes in a coarse-to-fine manner. The method is efficient, because i) it uses the same features extracted for detection, ii) it aggregates features using integral images, and iii) it avoids a dense evaluation of the proposals due to the inverse coarse-to-fine cascade. The method is also accurate, it outperforms most of the previously proposed object proposals approaches and when plugged into a CNN-based detector produces state-of-the-art detection performance.
Keywords :
"Proposals","Feature extraction","Detectors","Image edge detection","Object detection","Pipelines","Aggregates"
Publisher :
ieee
Conference_Titel :
Computer Vision (ICCV), 2015 IEEE International Conference on
Electronic_ISBN :
2380-7504
Type :
conf
DOI :
10.1109/ICCV.2015.296
Filename :
7410653
Link To Document :
بازگشت