TY  - CONF
AU  - Marc Masana
AU  - Joost Van de Weijer
AU  - Andrew Bagdanov
A2  - ICLR
PY  - 2016//
TI  - On-the-fly Network pruning for object detection
BT  - International conference on learning representations
N2  - Object detection with deep neural networks is often performed by passing a fewthousand candidate bounding boxes through a deep neural network for each image.These bounding boxes are highly correlated since they originate from the sameimage. In this paper we investigate how to exploit feature occurrence at the image scale to prune the neural network which is subsequently applied to all bounding boxes. We show that removing units which have near-zero activation in the image allows us to significantly reduce the number of parameters in the network. Results on the PASCAL 2007 Object Detection Challenge demonstrate that up to 40% of units in some fully-connected layers can be entirely eliminated with little change in the detection result.
L1  - http://refbase.cvc.uab.es/files/MVB2016.pdf
N1  - LAMP; 600.068; 600.106; 600.079
ID  - Marc Masana2016
ER  -