CBASH: Combined Backbone and Advanced Selection Heads With Object Semantic Proposals for Weakly Supervised Object Detection

Most recent object detection methods have achieved growing performance on public datasets. However, enormous efforts are needed for these methods due to the extensive annotations of ground-truth boxes. Weakly Supervised Object Detection (WSOD) methods hence have been proposed to solve this problem as only image-level annotations are required and then output bounding boxes related to the objects. In order to further elevate the weakly supervised detection methods on the extraction of reasonable features, the training of potential positive proposals, and the generation of proposals before training, we propose a new Combined Backbone and Advanced Selection Heads (CBASH) method with the proposals generated from the object semantic information. Specifically, Combined Backbone will make the unobvious object features more noticeable, Advanced Selection Heads promote more potential positive proposals to get training, and the generated object semantic proposals elevate the quality and quantity of positive proposals. The proposed method is evaluated on the challenging PASCAL VOC 2007 and 2012 benchmark datasets. Experimental results show that our proposed method can achieve improved performance on both VOC 2007 and VOC 2012 datasets and outperforms the existing state-of-the-art methods.

I. Introduction

With the amazing performance achieved by Convolutional Neural Network (CNN) model on multiple computer vision tasks such as image classification [1]–[3], object detection [4]–[10], and image segmentation [11]–[13], more advanced neural networks with various strengths are proposed to improve further. However, in object detection, fully supervised methods with massive anchor boxes [4]–[6] or anchor points [7]–[9] are in the majority, which compel researchers to put much attention on precisely annotating the coordinates of ground-truth boxes for each object before training.