Unsupervised Domain Adaptation for Depth Prediction from Images
- 12 September 2019
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 42 (10) , 2396-2409
Abstract
State-of-the-art methods to infer dense and accurate depth measurements from images rely on deep CNN models trained in an end-to-end fashion on a significant amount of data. However, despite the outstanding performance achieved, these frameworks suffer a drastic drop in accuracy when dealing with unseen environments much different, concerning appearance (e.g., synthetic vs. real) or context (e.g., indoor vs. outdoor), from those observed during the training phase. Such domain shift issue is usually softened by fine-tuning on smaller sets of images with depth labels acquired in the target domain with active sensors (e.g., LiDAR). However, relying on such supervised labeled data is seldom feasible in practical applications. Therefore, we propose an effective unsupervised domain adaptation technique enabling to overcome the domain shift problem without requiring any groundtruth label. Our method, deploying much more accessible to obtain stereo pairs, leverages traditional and not learning-based stereo algorithms to produce disparity/depth labels and on confidence measures to assess their degree of reliability. With these cues, we can fine-tune deep models through a novel confidence-guided loss function, neglecting the effect of outliers gathered from the output of conventional stereo algorithms.Keywords
All Related Versions
This publication has 59 references indexed in Scilit:
- Learning Depth from Single Monocular Images Using Deep Convolutional Neural FieldsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- A Deep Visual Correspondence Embedding Model for Stereo Matching Costs2015
- Object scene flow for autonomous vehicles2015
- Computing the stereo matching cost with a convolutional neural network2015
- High-Resolution Stereo Datasets with Subpixel-Accurate Ground Truth2014
- PM-Huber: PatchMatch with Huber Regularization for Stereo Matching2013
- Vision meets robotics: The KITTI datasetThe International Journal of Robotics Research, 2013
- Ensemble Learning for Confidence Measures in Stereo Vision2013
- Accurate and Efficient Stereo Processing by Semi-Global Matching and Mutual Information2005
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004