Do More Dropouts in Pool5 Feature Maps for Better Object Detection
This is an incremental improvement for object detection tasks, particularly beneficial in data-scarce scenarios.
The paper tackles the problem of improving object detection when training data is limited by editing CNN feature vectors to abandon those corresponding to unfriendly concepts, resulting in improved mean average precision on VOC datasets (e.g., 60.1% on VOC 2007).
Deep Convolutional Neural Networks (CNNs) have gained great success in image classification and object detection. In these fields, the outputs of all layers of CNNs are usually considered as a high dimensional feature vector extracted from an input image and the correspondence between finer level feature vectors and concepts that the input image contains is all-important. However, fewer studies focus on this deserving issue. On considering the correspondence, we propose a novel approach which generates an edited version for each original CNN feature vector by applying the maximum entropy principle to abandon particular vectors. These selected vectors correspond to the unfriendly concepts in each image category. The classifier trained from merged feature sets can significantly improve model generalization of individual categories when training data is limited. The experimental results for classification-based object detection on canonical datasets including VOC 2007 (60.1%), 2010 (56.4%) and 2012 (56.3%) show obvious improvement in mean average precision (mAP) with simple linear support vector machines.