In this paper, we design a simple yet powerful deep network architecture, U$^2$-Net, for salient object detection (SOD).
Ranked #1 on Salient Object Detection on HKU-IS
Such design fully capitalizes on the contextual information among input keys to guide the learning of dynamic attention matrix and thus strengthens the capacity of visual representation.
In recent years, there have been significant advances in building end-to-end Machine Learning (ML) systems that learn at scale.
RS Loss supervises the classifier, a sub-network of these methods, to rank each positive above all negatives as well as to sort positives among themselves with respect to (wrt.)
Derived regions are consistent across different images and coincide with human-defined semantic classes on some datasets.