Localization-aware Channel Pruning for Object Detection
share
Channel pruning is one of the important methods for deep model compression. Most of existing pruning methods mainly focus on classification. Few of them are designed for object detection. However, object detection is different from classification, which requires not only semantic information but also localization information. In this paper, we propose a localization-aware auxiliary network to find out the channels with key information for classification and regression so that we can conduct channel pruning directly for object detection, which saves lots of time and computing resources. In order to capture the localization information, we first design the auxiliary network with a local feature extraction layer which can obtain precise localization information of the default boxes by pixel alignment. Then, we propose an algorithm for adaptively adjusting the sampling area which enlarges the receptive fields of the default boxes when pruning shallow layers. Finally, we propose a scale-aware loss function which tends to keep the channels that contain the key information for classification and regression of small objects. Extensive experiments demonstrate the effectiveness of our method. On VOC2007, we prune 70% parameters of the SSD based on ResNet-50 with modest accuracy drop, which outperforms the-state-of-art method.
READ FULL TEXT