Learning Visual Object Classifiers with only Positive Images

Abstract:

In this paper, a novel approach is proposed for learning visual object classifiers with only positive images. Both positive and negative examples are collected from the positive images, and the false negative examples are filtered out by the Ramp Loss function, which has a strong ability of suppressing the influence of outliers. Meanwhile, the Latent Structural Support Vector Machines are adopted to estimate the best bounding boxes due to the unavoidable annotation errors. In learning the sub-problems, an extremely fast learning algorithm, CCCP-SGD, is proposed to optimize the Ramp Loss-based SVMs based on the Stochastic Gradient Descent algorithm. Experiments demonstrate that the CCCP-SGD algorithm can reduce the computing time both in the training and predicting phases, especially with a significant speedup in training, whilst it can also yield robust generalization performance when dataset is noisy. Besides, the visual object classifiers learnt by our approach with only positive images almost have the same performance as the classifiers learned with both positive and negative examples in object detection tasks.

• Periodical: Advanced Materials Research (Volumes 468-471)
• Pages: 1891-1894
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.468-471.1891
• Online since: February 2012
• Authors: Jia Bao Wang, Ya Fei Zhang, Jian Jiang Lu, Yang Li
• Keywords: Concave-Convex Procedure, Latent Structural Support Vector Machines, Ramp Loss Function, Stochastic Gradient Descent, Visual Object Classifiers

References

[1] R. Collobert, J. Weston, L. Bottou: Trading convexity for scalability. In: Proc. Internat. Conf. on Machine Learning (2006), p.201–208.

DOI: 10.1145/1143844.1143870

[2] S. Ertekin, L. Bottou, C.L. Giles: Nonconvex online support vector machines. IEEE Trans. Pattern Anal. Machine Intell., vol. 33 (2011), p.368–381.

DOI: 10.1109/tpami.2010.109

[3] P.F. Felzenszwalb, R.B. Girshick, D. McAllester, D. Ramanan: Object detection with discriminatively trained part based models. IEEE Trans. Pattern Anal. Machine Intell., vol. 32 (2010), p.1627–1645.

DOI: 10.1109/tpami.2009.167

[4] A. Vedaldi, A. Zisserman: Structured output regression for detection with partial truncation. In: Proc. Advance in Neural Information Processing Systems (2009), p.1928–1936.

[5] A.L. Yuille, A.Rangarajan: The concave-convex procedure. Neural Comput., vol. 15 (2003), p.915–936.

DOI: 10.1162/08997660360581958

[6] C.-N. Yu, T. Joachims: Learning structural svms with latent variable. In: Proc. Internat. Conf. on Machine Learning (2009), p.1169–1176.

[7] L. Bottou, O. Bousquet: The tradeoffs of large scale learning. In: Proc. Advances in Neural Information Processing Systems (2008), p.161–168.