%0 Journal Article %A XIAO Zhenjiu %A KONG Xiangxu %A ZONG Jiaxu %A YANG Yueying %T Image Object Detection Algorithm Based on Adaptive Focal Loss %D 2021 %R 10.3778/j.issn.1002-8331.2104-0321 %J Computer Engineering and Applications %P 185-192 %V 57 %N 23 %X

Modern target detection algorithms still have the imbalance of positive and negative samples caused by the existing target detection architecture and the imbalance of hard and easy samples caused by the training data. The existing methods generally use resampling based on class frequency or reweighting based on class prediction probability. Although the imbalance of classes is alleviated, new super parameters are introduced, which requires a lot of manual adjustment for each training task. For this reason, a new loss function Adaptive Focal Loss is proposed on the basis of the existing Focal Loss, which makes the model focus on the more difficult samples and adjust the super parameters adaptively. Firstly, according to the number of positive and negative samples in each batch of image tags in the training process, the self-adaptive weighting factor is calculated to achieve the dynamic balance of positive and negative samples. Secondly, according to the expected probabilities of all kinds of ground-truth label in different stages of the training process, the adaptive modulation factor is calculated, and the adaptive balanced samples are obtained. In order to verify the effectiveness of the method, the mAP of PASCAL VOC2007 test data set reaches 80.75%, which is 3.45 percentage points higher than the original algorithm. In PASCAL VOC2012 test data set, the mAP is 77.17%, which is 1.87 percentage points higher than the original algorithm. The experimental results show that, compared with the original Focal Loss, the detection accuracy of Adaptive Focal Loss is improved, and it has great practical value.

%U http://cea.ceaj.org/EN/10.3778/j.issn.1002-8331.2104-0321