Abstract
Object detection is an important step in automated scene understanding. Training state-of-the-art object detectors typically require manual annotation of training data which can be labor-intensive. In this paper, we propose a novel algorithm to automatically adapt a pedestrian detector trained on a generic image dataset to a video in an unsupervised way using joint dataset deep feature learning. Our approach does not require any background subtraction or tracking in the video. Experiments on two challenging video datasets show that our algorithm is effective and outperforms the state-of-the-art approach.
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
Preview
Unable to display preview. Download preview PDF.
References
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR (1), pp. 886–893 (2005)
Dollár, P., Wojek, C., Schiele, B., Perona, P.: Pedestrian detection: A benchmark. In: CVPR, pp. 304–311 (2009)
Everingham, M., Gool, L.J.V., Williams, C.K.I., Winn, J.M., Zisserman, A.: The pascal visual object classes (voc) challenge. International Journal of Computer Vision 88(2), 303–338 (2010)
Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: International Conference on Artificial Intelligence and Statistics, pp. 249–256 (2010)
Gong, B., Shi, Y., Sha, F., Grauman, K.: Geodesic flow kernel for unsupervised domain adaptation. In: CVPR, pp. 2066–2073 (2012)
Gopalan, R., Li, R., Chellappa, R.: Domain adaptation for object recognition: An unsupervised approach. In: ICCV, pp. 999–1006 (2011)
Tang, K., Ramanathan, V., Fei-Fei, L., Koller, D.: Shifting weights: Adapting object detectors from image to video. In: Neural Information Processing Systems (NIPS) (2012)
Levina, E., Bickel, P.J.: Maximum likelihood estimation of intrinsic dimension. In: Advances in Neural Information Processing Systems, pp. 777–784 (2004)
Martens, J.: Deep learning via hessian-free optimization. In: Proceedings of the 27th International Conference on Machine Learning (ICML 2010), pp. 735–742 (2010)
Ngiam, J., Coates, A., Lahiri, A., Prochnow, B., Ng, A., Le, Q.V.: On optimization methods for deep learning. In: Proceedings of the 28th International Conference on Machine Learning (ICML 2011), pp. 265–272 (2011)
Torralba, A., Efros, A.A.: Unbiased look at dataset bias. In: 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1521–1528. IEEE (2011)
Wang, M., Li, W., Wang, X.: Transferring a generic pedestrian detector towards specific scenes. In: CVPR, pp. 3274–3281 (2012)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Htike, K.K., Hogg, D. (2014). Unsupervised Detector Adaptation by Joint Dataset Feature Learning. In: Chmielewski, L.J., Kozera, R., Shin, BS., Wojciechowski, K. (eds) Computer Vision and Graphics. ICCVG 2014. Lecture Notes in Computer Science, vol 8671. Springer, Cham. https://doi.org/10.1007/978-3-319-11331-9_33
Download citation
DOI: https://doi.org/10.1007/978-3-319-11331-9_33
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-11330-2
Online ISBN: 978-3-319-11331-9
eBook Packages: Computer ScienceComputer Science (R0)