Liangliang Cao
ABSTRACT
This paper considers the problem of fine-grained image recognition with a growing vocabulary. Since in many real world applications we often have to add a new object category or visual concept with just a few images to learn from, it is crucial to develop a method that is able to generalize the recognition model from existing classes to new classes. Deep convolutional neural networks are capable of constructing powerful image representations; however, these networks usually rely on a logistic loss function that cannot handle the incremental learning problem. In this paper, we present a new method that can efficiently learn a new class given only a limited number of training examples, which we evaluate on the problems of food and clothing recognition. To illustrate the performance of our proposed method on the task of recognizing different kinds of food, when using only 1.3\% of training examples per category we achieved about 73\% of the performance (as measured by F1-score) compared to when using all available training data.
- R. Ando and T. Zhang. A framework for learning predictive structures from multiple tasks and unlabeled data. In JMLR, pages 1817--1853, 2005. Google Scholar
Digital Library
- G. Andrew and J. Gao. Scalable training of L1-regularized log-linear models. In ICML, 2007. Google ScholarDigital Library
- J. Bergstra, O. Breuleux, F. Bastien, P. Lamblin, R. Pascanu, G. Desjardins, J. Turian, D. Warde-Farley, and Y. Bengio. Theano: a CPU and GPU math expression compiler. In SciPy, 2010.Google ScholarCross Ref
- L. Bossard, M. Guillaumin, and L. Van Gool. Food-101 -- mining discriminative components with random forests. In ECCV, 2014.Google ScholarCross Ref
- K. Chatfield, K. Simonyan, A. Vedaldi, and A. Zisserman. Return of the devil in the details: delving deep into convolutional nets. In BMVC, 2014.Google ScholarCross Ref
- X. Chen, A. Shrivastava, and A. Gupta. NEIL: Extracting Visual Knowledge from Web Data. In ICCV, 2013. Google ScholarDigital Library
- S. Guadarrama, E. Rodner, K. Saenko, N. Zhang, R. Farrell, J. Donahue, and T. Darrell. Open-vocabulary object retrieval. Robotics: Science and Systems, 2014.Google ScholarCross Ref
- M. Hasan and A. Roy-Chowdhury. Incremental activity modeling and recognition in streaming videos. In CVPR, 2014. Google ScholarDigital Library
- S. Karayev, M. Trentacoste, H. Han, A. Agarwala, T. Darrell, A. Hertzmann, and H. Winnemoeller. Recognizing image style. In BMVC, 2014.Google ScholarCross Ref
- A. Krizhevsky, I. Sutskever, and G. Hinton. ImageNet classification with deep convolutional neural networks. In NIPS, 2012.Google ScholarDigital Library
- A. Kuznetsova, S. Hwang, B. Rosenhahn, and L. Sigal. Expanding object detector's horizon: incremental learning framework for object detection in videos. In CVPR, 2015.Google ScholarCross Ref
- M. Lin, Q. Chen, and S. Yan. Network in network. ICLR, 2013.Google Scholar
- T. Mensink, J. Verbeek, F. Perronnin, and G. Csurka. Distance-based image classification: Generalizing to new classes at near-zero cost. TPAMI, 35(11):2624--2637, 2013. Google ScholarDigital Library
- Y. Nesterov. A method of solving a convex programming problem with convergence rate O(1/k2). Soviet Mathematics Doklady, 27(2):372--376, 1983.Google Scholar
- A. Razavian, H. Azizpour, J. Sullivan, and S. Carlsson. CNN features off-the-shelf: an astounding baseline for recognition. CoRR, abs/1403.6382, 2014. Google ScholarDigital Library
- M. Ristin, M. Guillaumin, J. Gall, and L. Van Gool. Incremental learning of NCM forests for large-scale image classification. In CVPR, 2014. Google ScholarDigital Library
- K. Simonyan and A. Zisserman. Very deep convolutional networks for large-scale image recognition. In ICLR, 2015.Google Scholar
- C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich. Going deeper with convolutions. In CVPR, 2015.Google ScholarCross Ref
Index Terms
- Incremental Learning for Fine-Grained Image Recognition
Recommendations
Mid‐level deep Food Part mining for food image recognition
There has been a growing interest in food image recognition for a wide range of applications. Among existing methods, mid‐level image part‐based approaches show promising performances due to their suitability for modelling deformable food parts (FPs). ...
Improved softmax loss for deep learning‐based face and expression recognition
In recent years, deep convolutional neural networks (CNN) have been widely used in computer vision and significantly improved the performance of image recognition tasks. Most works use softmax loss to supervise the training of CNN and then adopt the ...
Incremental Learning for Compressed Pornographic Image Recognition
BIGMM '15: Proceedings of the 2015 IEEE International Conference on Multimedia Big DataA compressed pornographic image recognition method is proposed by using incremental learning. For describing pornographic image, visual words are created from low-resolution (LR) image reconstructed from the compressed stream of the pornographic image. ...
Comments