A probabilistic model for recursive factorized image features
Sergey Karayev, Mario Fritz, Sanja Fidler et al. · 2011
Layered representations for object recognition are important due to their increased invariance, biological plausibility, and computational benefits. However, most of existing approaches to hierarchical representations are strictly feedforward, and thus not well able to resolve local ambiguities. We propose a probabilistic model that learns and infers all layers of the hierarchy jointly. Specifically, we suggest a process of recursive probabilistic factorization, and present a novel generative model based on Latent Dirichlet Allocation to this end. The approach is tested on a standard recognition dataset, outperforming existing hierarchical approaches and demonstrating performance on par with current single-feature state-of-the-art models. We demonstrate two important properties of our proposed model: 1) adding an additional layer to the representation increases performance over the flat model; 2) a full Bayesian approach outperforms a feedforward implementation of the model.
Cited by 6 works. doi:10.1109/cvpr.2011.5995728
Authors
References
- Distinctive Image Features from Scale-Invariant Keypoints
- A Fast Learning Algorithm for Deep Belief Nets
- Latent dirichlet allocation
- Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories
- What is the best multi-stage architecture for object recognition?
- Video Google: a text retrieval approach to object matching in videos
- Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations
- Learning generative visual models from few training examples: An incremental Bayesian approach tested on 101 object categories
- Sparse coding with an overcomplete basis set: A strategy employed by V1?
- Linear spatial pyramid matching using sparse coding for image classification