Robust Deep Learning with Active Noise Cancellation for Spatial Computing

This paper proposes CANC, a Co-teaching Active Noise Cancellation method, applied in spatial computing to address deep learning trained with extreme noisy labels. Deep learning algorithms have been successful in spatial computing for land or building footprint recognition. However a lot of noise exists in ground truth labels due to how labels are collected in spatial computing and satellite imagery. Existing methods to deal with extreme label noise conduct clean sample selection and do not utilize the remaining samples. Such techniques can be wasteful due to the cost of data retrieval. Our proposed CANC algorithm not only conserves high-cost training samples but also provides active label correction to better improve robust deep learning with extreme noisy labels. We demonstrate the effectiveness of CANC for building footprint recognition for spatial computing.

[1]  Swapnil Udar,et al.  Extracting Building Footprints from Satellite Images using Convolutional Neural Networks , 2018, 2018 International Conference on Advances in Computing, Communications and Informatics (ICACCI).

[2]  Timo Aila,et al.  Temporal Ensembling for Semi-Supervised Learning , 2016, ICLR.

[3]  Naresh Manwani,et al.  Noise Tolerance Under Risk Minimization , 2011, IEEE Transactions on Cybernetics.

[4]  Yoshua Bengio,et al.  A Closer Look at Memorization in Deep Networks , 2017, ICML.

[5]  Aritra Ghosh,et al.  Making risk minimization tolerant to label noise , 2014, Neurocomputing.

[6]  Geoffrey E. Hinton,et al.  Machine Learning for Aerial Image Labeling , 2013 .

[7]  C. V. Jawahar,et al.  Improved Road Connectivity by Joint Learning of Orientation and Segmentation , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Xianming Liu,et al.  Mapping the world population one building at a time , 2017, ArXiv.

[9]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Tailin Wu,et al.  Learning with Confident Examples: Rank Pruning for Robust Classification with Noisy Labels , 2017, UAI.

[11]  Lianru Gao,et al.  Building Extraction from High-Resolution Aerial Imagery Using a Generative Adversarial Network with Spatial and Channel Attention Mechanisms , 2019, Remote. Sens..

[12]  Yizhou Wang,et al.  L_DMI: A Novel Information-theoretic Loss Function for Training Deep Nets Robust to Label Noise , 2019, NeurIPS.

[13]  Adam Van Etten,et al.  SpaceNet: A Remote Sensing Dataset and Challenge Series , 2018, ArXiv.

[14]  Shai Shalev-Shwartz,et al.  Decoupling "when to update" from "how to update" , 2017, NIPS.

[15]  Li Fei-Fei,et al.  MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels , 2017, ICML.

[16]  Aditya Krishna Menon,et al.  Learning with Symmetric Label Noise: The Importance of Being Unhinged , 2015, NIPS.

[17]  Le Song,et al.  Iterative Learning with Open-set Noisy Labels , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[18]  Thomas Hofmann,et al.  Learning Aerial Image Segmentation From Online Maps , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[19]  Saikat Basu,et al.  Building High Resolution Maps for Humanitarian Aid and Development with Weakly- and Semi-Supervised Learning , 2019, CVPR Workshops.

[20]  David J. Hand,et al.  An Empirical Comparison of Three Boosting Algorithms on Real Data Sets with Artificial Class Noise , 2003, Multiple Classifier Systems.

[21]  Masashi Sugiyama,et al.  On Symmetric Losses for Learning from Corrupted Labels , 2019, ICML.

[22]  Jacob Goldberger,et al.  Training deep neural-networks using a noise adaptation layer , 2016, ICLR.

[23]  Xingrui Yu,et al.  Co-teaching: Robust training of deep neural networks with extremely noisy labels , 2018, NeurIPS.

[24]  Görkem Algan,et al.  Label Noise Types and Their Effects on Deep Learning , 2020, ArXiv.

[25]  Jing Huang,et al.  DeepGlobe 2018: A Challenge to Parse the Earth through Satellite Images , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[26]  Xianming Liu,et al.  Hyperspectral Image Classification in the Presence of Noisy Labels , 2018, IEEE Transactions on Geoscience and Remote Sensing.

[27]  Dumitru Erhan,et al.  Training Deep Neural Networks on Noisy Labels with Bootstrapping , 2014, ICLR.

[28]  Tieniu Tan,et al.  A Light CNN for Deep Face Representation With Noisy Labels , 2015, IEEE Transactions on Information Forensics and Security.