Salient Object Detection
184 papers with code • 6 benchmarks • 16 datasets
In this paper, we design a simple yet powerful deep network architecture, U$^2$-Net, for salient object detection (SOD).
We further design a feature aggregation module (FAM) to make the coarse-level semantic information well fused with the fine-level features from the top-down pathway.
Furthermore, different from binary cross entropy, the proposed PPA loss doesn't treat pixels equally, which can synthesize the local structure information of a pixel to guide the network to focus more on local details.
Benefiting from the quick development of deep convolutional neural networks, especially fully convolutional neural networks (FCNs), remarkable progresses have been achieved on salient object detection recently.