Multi-Task Learning for Single Image Depth Estimation and Segmentation Based on Unsupervised Network | IEEE Conference Publication | IEEE Xplore

Multi-Task Learning for Single Image Depth Estimation and Segmentation Based on Unsupervised Network


Abstract:

Deep neural networks have significantly enhanced the performance of various computer vision tasks, including single image depth estimation and image segmentation. However...Show More

Abstract:

Deep neural networks have significantly enhanced the performance of various computer vision tasks, including single image depth estimation and image segmentation. However, most existing approaches handle them in supervised manners and require a large number of ground truth labels that consume extensive human efforts and are not always available in real scenarios. In this paper, we propose a novel framework to estimate disparity maps and segment images simultaneously by jointly training an encoder-decoder-based interactive convolutional neural network (CNN) for single image depth estimation and a multiple class CNN for image segmentation. Learning the neural network for one task can be beneficial from simultaneously learning from another one under a multi-task learning framework. We show that our proposed model can learn per-pixel depth regression and segmentation from just a single image input. Extensive experiments on available public datasets, including KITTI, Cityscapes urban, and PASCAL-VOC demonstrate the effectiveness of our model compared with other state-of-the-art methods for both tasks.
Date of Conference: 31 May 2020 - 31 August 2020
Date Added to IEEE Xplore: 15 September 2020
ISBN Information:

ISSN Information:

Conference Location: Paris, France

References

References is not available for this document.