The current mainstream weakly supervised object detection methods based on image-level annotation often occur local localization problem, tend to overfit the most discriminative regions, and ignore object integrity. To solve these existing problems, an end-to-end weakly supervised object detection network based on feature self-distillation (FSD-Net), in which the detachable feature self-distillation module fully uses the semantic and detailed information in the representation of different hierarchical features, is proposed. Additionally, through feature self-distillation loss constraint network training, the comprehensive performance of the detector is enhanced without increasing the calculation cost during the test period. Moreover, the regression branches are constructed to simply extract and effectively utilize the implicit location information in the features, improves the original supervision information generation algorithm, and balances optimization loss and other strategies to further improve the local localization problem of the weakly supervised object detector. Experiments on large-scale public datasets, such as Pascal VOC 2007, VOC 2012, and MS-COCO, show that FSD-Net has a better detection performance than the Baseline and other existing mainstream methods, effectively alleviating the local localization problem in weakly supervised object detection.