Abstract
Active learning—a class of algorithms that iteratively searches for the most informative samples to include in a training dataset—has been shown to be effective at annotating data for image classification. However, the use of active learning for object detection is still largely unexplored as determining informativeness of an object-location hypothesis is more difficult. In this paper, we address this issue and present two metrics for measuring the informativeness of an object hypothesis, which allow us to leverage active learning to reduce the amount of annotated data needed to achieve a target object detection performance. Our first metric measures “localization tightness” of an object hypothesis, which is based on the overlapping ratio between the region proposal and the final prediction. Our second metric measures “localization stability” of an object hypothesis, which is based on the variation of predicted object locations when input images are corrupted by noise. Our experimental results show that by augmenting a conventional active-learning algorithm designed for classification with the proposed metrics, the amount of labeled training data required can be reduced up to 25%. Moreover, on PASCAL 2007 and 2012 datasets our localization-stability method has an average relative improvement of 96.5% and 81.9% over the baseline method using classification only.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Bietti, A.: Active learning for object detection on satellite images. Technical report, California Institute of Technology, January 2012
Dai, J., He, K., Sun, J.: Instance-aware semantic segmentation via multi-task network cascades. In: CVPR (2016)
Dai, J., Li, Y., He, K., Sun, J.: R-FCN: object detection via region-based fully convolutional networks. In: NIPS (2016)
Dutt Jain, S., Grauman, K.: Active image segmentation propagation. In: CVPR (2016)
Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL Visual Object Classes (VOC) challenge. Int. J. Comput. Vis. 88(2), 303–338 (2010)
Freytag, A., Rodner, E., Denzler, J.: Selecting influential examples: active learning with expected model output changes. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8692, pp. 562–577. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10593-2_37
Girshick, R.: Fast R-CNN. In: ICCV (2015)
Hasan, M., Roy-Chowdhury, A.K.: Continuous learning of human activity models using deep nets. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8691, pp. 705–720. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10578-9_46
Hasan, M., Roy-Chowdhury, A.K.: Context aware active learning of activity recognition models. In: ICCV (2015)
Hoffman, J., et al.: LSDA: large scale detection through adaptation. In: NIPS (2014)
Huijser, M., van Gemert, J.C.: Active decision boundary annotation with deep generative models. In: ICCV (2017)
Islam, R.: Active learning for high dimensional inputs using Bayesian convolutional neural networks. Master’s thesis, Department of Engineering, University of Cambridge, August 2016
Kapoor, A., Grauman, K., Urtasun, R., Darrell, T.: Active learning with Gaussian processes for object categorization. In: ICCV (2007)
Kapoor, A., Grauman, K., Urtasun, R., Darrell, T.: Gaussian processes for object categorization. Int. J. Comput. Vis. 88(2), 169–188 (2010). https://doi.org/10.1007/s11263-009-0268-3
Karasev, V., Ravichandran, A., Soatto, S.: Active frame, location, and detector selection for automated and manual video annotation. In: CVPR (2014)
Konyushkova, K., Sznitman, R., Fua, P.: Introducing geometry in active learning for image segmentation. In: ICCV (2015)
Lewis, D.D., Catlett, J.: Heterogeneous uncertainty sampling for supervised learning. In: ICML (1994)
Lin, T.Y., Goyal, P., Girshick, R., He, K., Dollar, P.: Focal loss for dense object detection. In: ICCV (2017)
Lin, T.Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740–755. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10602-1_48
Liu, W., et al.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21–37. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46448-0_2
Najibi, M., Rastegari, M., Davis, L.S.: G-CNN: an iterative grid based object detector. In: CVPR (2016)
Papadopoulos, D.P., Uijlings, J.R.R., Keller, F., Ferrari, V.: We don’t need no bounding-boxes: training object class detectors using only human verification. In: CVPR (2016)
Prest, A., Leistner, C., Civera, J., Schmid, C., Ferrari, V.: Learning object class detectors from weakly annotated video. In: CVPR (2012)
Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: CVPR (2016)
Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. In: CVPR (2017)
Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS (2015)
Russakovsky, O., Li, L.J., Fei-Fei, L.: Best of both worlds: human-machine collaboration for object annotation. In: CVPR (2015)
Settles, B.: Active learning literature survey. Univ. Wis. Madison 52(55–66), 11 (2010)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
Sivaraman, S., Trivedi, M.M.: Active learning for on-road vehicle detection: a comparative study. Mach. Vis. Appl. 25(3), 599–611 (2014). https://doi.org/10.1007/s00138-011-0388-y
Stark, F., Hazirbas, C., Triebel, R., Cremers, D.: Captcha recognition with active deep learning. In: GCPR Workshop on New Challenges in Neural Computation, Aachen, Germany (2015)
Su, H., Deng, J., Fei-Fei, L.: Crowdsourcing annotations for visual object detection. In: Workshops at the Twenty-Sixth AAAI Conference on Artificial Intelligence (2012)
Miyato, T., Maeda, S.I., Koyama, M., Nakae, K., Ishii, S.: Distributional smoothing with virtual adversarial training. In: ICLR (2016)
Tong, S., Koller, D.: Support vector machine active learning with applications to text classification. J. Mach. Learn. Res. 2, 45–66 (2002)
Uijlings, J.R.R., van de Sande, K.E.A., Gevers, T., Smeulders, A.W.M.: Selective search for object recognition. Int. J. Comput. Vis. 104(2), 154–171 (2013)
Vijayanarasimhan, S., Grauman, K.: Large-scale live active learning: training object detectors with crawled data and crowds. Int. J. Comput. Vis. 108(1–2), 97–114 (2014)
Yoo, D., Park, S., Lee, J., Paek, A.S., Kweon, I.: AttentionNet: aggregating weak directions for accurate object detection. In: ICCV, pp. 2659–2667 (2015)
Zhang, S., Wen, L., Bian, X., Lei, Z., Li, S.Z.: Single-shot refinement neural network for object detection. In: CVPR (2018)
Acknowledgments
This work was conducted during the first author’s internship in Mitsubishi Electric Research Laboratories. This work was sponsored in part by National Science Foundation grant #13-21168.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Kao, CC., Lee, TY., Sen, P., Liu, MY. (2019). Localization-Aware Active Learning for Object Detection. In: Jawahar, C., Li, H., Mori, G., Schindler, K. (eds) Computer Vision – ACCV 2018. ACCV 2018. Lecture Notes in Computer Science(), vol 11366. Springer, Cham. https://doi.org/10.1007/978-3-030-20876-9_32
Download citation
DOI: https://doi.org/10.1007/978-3-030-20876-9_32
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-20875-2
Online ISBN: 978-3-030-20876-9
eBook Packages: Computer ScienceComputer Science (R0)