Active Learning for Deep Object Detection

The great success that deep models have achieved in the past is mainly owed to large amounts of labeled training data. However, the acquisition of labeled data for new tasks aside from existing benchmarks is both challenging and costly. Active learning can make the process of labeling new data more efficient by selecting unlabeled samples which, when labeled, are expected to improve the model the most. In this paper, we combine a novel method of active learning for object detection with an incremental learning scheme to enable continuous exploration of new unlabeled datasets. We propose a set of uncertainty-based active learning metrics suitable for most object detectors. Furthermore, we present an approach to leverage class imbalances during sample selection. All methods are evaluated systematically in a continuous exploration context on the PASCAL VOC 2012 dataset.

[1]  Kaiming He,et al.  Feature Pyramid Networks for Object Detection , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Ali Farhadi,et al.  YOLO9000: Better, Faster, Stronger , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Joachim Denzler,et al.  Fine-Tuning Deep Neural Networks in Continuous Learning Scenarios , 2016, ACCV Workshops.

[4]  David Cohn,et al.  Active Learning , 2010, Encyclopedia of Machine Learning.

[5]  Trevor Darrell,et al.  Gaussian Processes for Object Categorization , 2010, International Journal of Computer Vision.

[6]  C. Lee Giles,et al.  Learning on the border: active learning in imbalanced data classification , 2007, CIKM '07.

[7]  Ali Farhadi,et al.  YOLOv3: An Incremental Improvement , 2018, ArXiv.

[8]  Daphne Koller,et al.  Support Vector Machine Active Learning with Applications to Text Classification , 2000, J. Mach. Learn. Res..

[9]  Trevor Darrell,et al.  Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[10]  Ali Farhadi,et al.  You Only Look Once: Unified, Real-Time Object Detection , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[11]  Burr Settles,et al.  Active Learning Literature Survey , 2009 .

[12]  Cordelia Schmid,et al.  Incremental Learning of Object Detectors without Catastrophic Forgetting , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[13]  Y. Freund,et al.  Active learning for visual object detection , 2005 .

[14]  Vinay P. Namboodiri,et al.  Active learning with version spaces for object detection , 2016, ArXiv.

[15]  Hairong Liu,et al.  Active Learning for Speech Recognition: the Power of Gradients , 2016, ArXiv.

[16]  Joachim Denzler,et al.  Watch, Ask, Learn, and Improve: a lifelong learning cycle for visual recognition , 2016, ESANN.

[17]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[18]  Luc Van Gool,et al.  The Pascal Visual Object Classes (VOC) Challenge , 2010, International Journal of Computer Vision.

[19]  Koen E. A. van de Sande,et al.  Selective Search for Object Recognition , 2013, International Journal of Computer Vision.

[20]  Frank Keller,et al.  We Don’t Need No Bounding-Boxes: Training Object Class Detectors Using Only Human Verification , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[21]  Ruimao Zhang,et al.  Cost-Effective Active Learning for Deep Image Classification , 2017, IEEE Transactions on Circuits and Systems for Video Technology.

[22]  Razvan Pascanu,et al.  Overcoming catastrophic forgetting in neural networks , 2016, Proceedings of the National Academy of Sciences.

[23]  Li Fei-Fei,et al.  Crowdsourcing in Computer Vision , 2016, Found. Trends Comput. Graph. Vis..

[24]  Daniel Cremers,et al.  CAPTCHA Recognition with Active Deep Learning , 2015 .

[25]  Yu-Pu Yang,et al.  A batch-mode active learning SVM method based on semi-supervised clustering , 2015, Intell. Data Anal..

[26]  Andreas Nürnberger,et al.  The Power of Ensembles for Active Learning in Image Classification , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[27]  Ross B. Girshick,et al.  Fast R-CNN , 2015, 1504.08083.

[28]  Peng Liu,et al.  Ieee Journal of Selected Topics in Applied Earth Observations and Remote Sensing 1 Active Deep Learning for Classification of Hyperspectral Images , 2022 .

[29]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[30]  Ming-Yu Liu,et al.  Deep Active Learning for Civil Infrastructure Defect Detection and Classification , 2017 .

[31]  Wei Liu,et al.  DSSD : Deconvolutional Single Shot Detector , 2017, ArXiv.

[32]  Kristen Grauman,et al.  Large-scale live active learning: Training object detectors with crawled data and crowds , 2011, CVPR.

[33]  Rong Jin,et al.  Large-scale text categorization by batch mode active learning , 2006, WWW '06.

[34]  Zoubin Ghahramani,et al.  Deep Bayesian Active Learning with Image Data , 2017, ICML.

[35]  Ashish Kapoor,et al.  Active learning for large multi-class problems , 2009, CVPR.

[36]  Luc Van Gool,et al.  Interactive object detection , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[37]  Joachim Denzler,et al.  Large-Scale Active Learning with Approximations of Expected Model Output Changes , 2016, GCPR.

[38]  Wei Liu,et al.  SSD: Single Shot MultiBox Detector , 2015, ECCV.