Salient instance segmentation with region and box-level annotations

In the field of saliency detection, salient instance segmentation is a novel challenging task that has received widespread attention. Due to the limited scale of the available dataset and the high cost of mask annotations, a substantial quantity of supervision sources is urgently required to train a high-performing salient instance model. To this end, we aim to train a novel salient instance segmentation model by weak supervisions that make full use of the existing salient object detection dataset. In this paper, we present a cyclic global context salient instance segmentation network (CGCNet) supervised by the combination of salient regions and bounding boxes from ready-made salient object detection datasets. To locate salient instances more accurately, a global feature refining layer is designed to expand the size of the features from the region of interest (ROI) to the global field in a scene. Moreover, a labeling updating scheme is embedded in the proposed framework to iteratively update the weak labels. Extensive experimental results demonstrate that our CGCNet trained by weak labels is competitive with the existing fully -supervised state-of-the-art methods.(c) 2022 Elsevier B.V. All rights reserved.

Automated summary

In this paper, a salient instance segmentation model trained by weak supervisions is proposed, which makes use of existing salient object detection datasets and combines salient regions and bounding boxes for supervision. With the global feature refining layer and labeling updating scheme, the model can accurately locate salient instances. Extensive experiments demonstrate the competitiveness of the proposed model trained by weak labels with the existing fully-supervised state-of-the-art methods.