DOOBNet: Deep Object Occlusion Boundary Detection from an Image
This work addresses object occlusion boundary detection for computer vision applications, representing an incremental improvement over existing methods.
The paper tackles the problem of object occlusion boundary detection by addressing class imbalance with a novel Attention Loss function and proposes DOOBNet, a multi-task network that achieves state-of-the-art results with ODS F-scores of 0.702 on PIOD and 0.555 on BSDS ownership datasets, and improves detection speed to 0.037s per image.
Object occlusion boundary detection is a fundamental and crucial research problem in computer vision. This is challenging to solve as encountering the extreme boundary/non-boundary class imbalance during training an object occlusion boundary detector. In this paper, we propose to address this class imbalance by up-weighting the loss contribution of false negative and false positive examples with our novel Attention Loss function. We also propose a unified end-to-end multi-task deep object occlusion boundary detection network (DOOBNet) by sharing convolutional features to simultaneously predict object boundary and occlusion orientation. DOOBNet adopts an encoder-decoder structure with skip connection in order to automatically learn multi-scale and multi-level features. We significantly surpass the state-of-the-art on the PIOD dataset (ODS F-score of .702) and the BSDS ownership dataset (ODS F-score of .555), as well as improving the detecting speed to as 0.037s per image on the PIOD dataset.