Unsupervised Domain Adaptation for Depth Prediction from Images

被引:50
|
作者
Tonioni, Alessio [1 ]
Poggi, Matteo [1 ]
Mattoccia, Stefano [1 ]
Di Stefano, Luigi [1 ]
机构
[1] Univ Bologna, Dept Comp Sci & Engn, BO-40126 Bologna, Italy
关键词
Training; Reliability; Estimation; Loss measurement; Computer architecture; Prediction algorithms; Deep learning; depth estimation; unsupervised learning; self-supervised learning; domain adaptation; COST AGGREGATION; STEREO; ACCURATE;
D O I
10.1109/TPAMI.2019.2940948
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
State-of-the-art approaches to infer dense depth measurements from images rely on CNNs trained end-to-end on a vast amount of data. However, these approaches suffer a drastic drop in accuracy when dealing with environments much different in appearance and/or context from those observed at training time. This domain shift issue is usually addressed by fine-tuning on smaller sets of images from the target domain annotated with depth labels. Unfortunately, relying on such supervised labeling is seldom feasible in most practical settings. Therefore, we propose an unsupervised domain adaptation technique which does not require groundtruth labels. Our method relies only on image pairs and leverages on classical stereo algorithms to produce disparity measurements alongside with confidence estimators to assess upon their reliability. We propose to fine-tune both depth-from-stereo as well as depth-from-mono architectures by a novel confidence-guided loss function that handles the measured disparities as noisy labels weighted according to the estimated confidence. Extensive experimental results based on standard datasets and evaluation protocols prove that our technique can address effectively the domain shift issue with both stereo and monocular depth prediction architectures and outperforms other state-of-the-art unsupervised loss functions that may be alternatively deployed to pursue domain adaptation.
引用
收藏
页码:2396 / 2409
页数:14
相关论文
共 50 条
  • [31] Unsupervised Domain Adaptation via Deep Conditional Adaptation Network
    Ge, Pengfei
    Ren, Chuan-Xian
    Xu, Xiao-Lin
    Yan, Hong
    PATTERN RECOGNITION, 2023, 134
  • [32] Unsupervised Personal Thermal Comfort Prediction via Adversarial Domain Adaptation
    Das, Hari Prasanna
    Schiavon, Stefano
    Spanos, Costas J.
    BUILDSYS'21: PROCEEDINGS OF THE 2021 ACM INTERNATIONAL CONFERENCE ON SYSTEMS FOR ENERGY-EFFICIENT BUILT ENVIRONMENTS, 2021, : 230 - 231
  • [33] Latent Domain Generation for Unsupervised Domain Adaptation Object Counting
    Zhang, Anran
    Yang, Yandan
    Xu, Jun
    Cao, Xianbin
    Zhen, Xiantong
    Shao, Ling
    IEEE TRANSACTIONS ON MULTIMEDIA, 2023, 25 (1773-1783) : 1773 - 1783
  • [34] Unsupervised Domain Adaptation in Semantic Segmentation: A Review
    Toldo, Marco
    Maracani, Andrea
    Michieli, Umberto
    Zanuttigh, Pietro
    TECHNOLOGIES, 2020, 8 (02)
  • [35] Guide Subspace Learning for Unsupervised Domain Adaptation
    Zhang, Lei
    Fu, Jingru
    Wang, Shanshan
    Zhang, David
    Dong, Zhaoyang
    Chen, C. L. Philip
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2020, 31 (09) : 3374 - 3388
  • [36] Unsupervised Domain Adaptation for Robust Sensory Systems
    Mathur, Akhil
    Isopoussu, Anton
    Berthouze, Nadia
    Lane, Nicholas D.
    Kawsar, Fahim
    UBICOMP/ISWC'19 ADJUNCT: PROCEEDINGS OF THE 2019 ACM INTERNATIONAL JOINT CONFERENCE ON PERVASIVE AND UBIQUITOUS COMPUTING AND PROCEEDINGS OF THE 2019 ACM INTERNATIONAL SYMPOSIUM ON WEARABLE COMPUTERS, 2019, : 505 - 509
  • [37] Unsupervised Domain Adaptation Based on Correlation Maximization
    Abdi, Lida
    Hashemi, Sattar
    IEEE ACCESS, 2021, 9 : 127054 - 127067
  • [38] Unsupervised Domain Adaptation With Label and Structural Consistency
    Hou, Cheng-An
    Tsai, Yao-Hung Hubert
    Yeh, Yi-Ren
    Wang, Yu-Chiang Frank
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2016, 25 (12) : 5552 - 5562
  • [39] Hierarchical optimal transport for unsupervised domain adaptation
    Mourad El Hamri
    Younès Bennani
    Issam Falih
    Machine Learning, 2022, 111 : 4159 - 4182
  • [40] Hierarchical optimal transport for unsupervised domain adaptation
    El Hamri, Mourad
    Bennani, Younes
    Falih, Issam
    MACHINE LEARNING, 2022, 111 (11) : 4159 - 4182