Timezone: »

DeepUSPS: Deep Robust Unsupervised Saliency Prediction via Self-supervision
Tam Nguyen · Maximilian Dax · Chaithanya Kumar Mummadi · Nhung Ngo · Thi Hoai Phuong Nguyen · Zhongyu Lou · Thomas Brox

Tue Dec 10 05:30 PM -- 07:30 PM (PST) @ East Exhibition Hall B + C #59

Deep neural network (DNN) based salient object detection in images based on high-quality labels is expensive. Alternative unsupervised approaches rely on careful selection of multiple handcrafted saliency methods to generate noisy pseudo-ground-truth labels. In this work, we propose a two-stage mechanism for robust unsupervised object saliency prediction, where the first stage involves refinement of the noisy pseudo labels generated from different handcrafted methods. Each handcrafted method is substituted by a deep network that learns to generate the pseudo labels. These labels are refined incrementally in multiple iterations via our proposed self-supervision technique. In the second stage, the refined labels produced from multiple networks representing multiple saliency methods are used to train the actual saliency detection network. We show that this self-learning procedure outperforms all the existing unsupervised methods over different datasets. Results are even comparable to those of fully-supervised state-of-the-art approaches.

Author Information

Tam Nguyen (Freiburg Computer Vision Lab)
Maximilian Dax (Bosch GmbH)
Chaithanya Kumar Mummadi (Bosch Center for Artificial Intelligence)
Nhung Ngo (Bosch Center for Artificial Intelligence)
Thi Hoai Phuong Nguyen (Karlsruhe Institute of Technology (KIT))
Zhongyu Lou (Robert Bosch Gmbh)
Thomas Brox (University of Freiburg)

More from the Same Authors