WSOD with PSNet and Box Regression
This work addresses the challenge of incomplete or inaccurate proposals in WSOD, which is important for reducing annotation costs in object detection tasks, though it appears incremental.
The paper tackled the problem of weakly supervised object detection (WSOD) by introducing a box regression module and a proposal scoring network (PSNet) to generate more accurate proposals, achieving significantly improved results on PASCAL VOC 2007 and 2012 datasets.
Weakly supervised object detection(WSOD) task uses only image-level annotations to train object detection task. WSOD does not require time-consuming instance-level annotations, so the study of this task has attracted more and more attention. Previous weakly supervised object detection methods iteratively update detectors and pseudo-labels, or use feature-based mask-out methods. Most of these methods do not generate complete and accurate proposals, often only the most discriminative parts of the object, or too many background areas. To solve this problem, we added the box regression module to the weakly supervised object detection network and proposed a proposal scoring network (PSNet) to supervise it. The box regression module modifies proposal to improve the IoU of proposal and ground truth. PSNet scores the proposal output from the box regression network and utilize the score to improve the box regression module. In addition, we take advantage of the PRS algorithm for generating a more accurate pseudo label to train the box regression module. Using these methods, we train the detector on the PASCAL VOC 2007 and 2012 and obtain significantly improved results.