Cascaded Partial Decoder for Fast and Accurate Salient Object Detection.
CVPR, (2019): 3907-3916
Existing state-of-the-art salient object detection networks rely on aggregating multi-level features of pre-trained convolutional neural networks (CNNs). Compared to high-level features, low-level features contribute less to performance but cost more computations because of their larger spatial resolutions. In this paper, we propose a nov...更多
下载 PDF 全文