Title :
A probabilistic model for recursive factorized image features
Author :
Karayev, Sergey ; Fritz, Mario ; Fidler, Sanja ; Darrell, Trevor
Author_Institution :
ICSI, UC Berkeley, Berkeley, CA, USA
Abstract :
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.
Keywords :
Bayes methods; feature extraction; feedforward; image representation; object recognition; probability; recursive estimation; Bayesian approach; feature extraction; feedforward; image representations; latent Dirichlet allocation; object recognition; probabilistic model; recursive probabilistic factorization; Biological system modeling; Computational modeling; Feedforward neural networks; Probabilistic logic; Resource management; Visualization; Vocabulary;
Conference_Titel :
Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on
Conference_Location :
Providence, RI
Print_ISBN :
978-1-4577-0394-2
DOI :
10.1109/CVPR.2011.5995728