# Do More Dropouts in Pool5 Feature Maps for Better Object Detection Source: [Do More Dropouts in Pool5 Feature Maps for Better Object Detection]() Collection index: [llms.txt]() Data updated: 2025-10-25T20:01:28.850Z Authors: Zhiqiang Shen, Xiangyang Xue Published: 2014-09-24T11:50:48.000Z ## Abstract 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Object Detection on PASCAL VOC 2012 (test)](): Object Detection; PASCAL VOC 2012 (test); mAP: 56.3. ## Original sources and implementation [Original paper]() [PDF]()