MPLA-Net: Multiple Pseudo Label Aggregation Network for Weakly Supervised Video Salient Object Detection
Chunjie Ma, Lina Du, Zhuo Li, Jiafeng Li
Abstract
Weakly Supervised Video Salient Object Detection (WSVSOD) only requires coarse-grained manual annotations, which can achieve a good trade-off between labeling efficiency and detection performance. In this paper, a Multiple Pseudo Label Aggregation Network (MPLA-Net) is proposed for WSVSOD. Firstly, the video frames that can obtain high-quality pseudo labels are selected to generate multiple pseudo labels, so as to avoid the prejudice of the single label. Moreover, the pseudo label with fine edge information is used to generate the Edge Information Map (EIM). Secondly, MPLA-Net is designed to adequately excavate and utilize the comprehensive saliency cues in multiple pseudo labels to improve the detection accuracy, in which ResNet-50 is adopted as the backbone network. Edge loss, pseudo label loss, self-supervised loss and fusion loss are exploited to jointly supervise and optimize the network training to obtain a robust detection model. Experimental results on five benchmark datasets demonstrate that, compared with existing weakly supervised methods, the proposed method can achieve state-of-the-art detection accuracy with less model parameters and higher detection speed. And the detected salient objects have fine boundaries.