Scene Classification Using a Hybrid Generative/Discriminative Approach Export

@article{citeulike:3047363, abstract = {We investigate whether dimensionality reduction using a latent generative model is beneficial for the task of weakly supervised scene classification. In detail, we are given a set of labeled images of scenes (for example, coast, forest, city, river, etc.), and our objective is to classify a new image into one of these categories. Our approach consists of first discovering latent ";topics"; using probabilistic Latent Semantic Analysis (pLSA), a generative model from the statistical text literature here applied to a bag of visual words representation for each image, and subsequently, training a multiway classifier on the topic distribution vector for each image. We compare this approach to that of representing each image by a bag of visual words vector directly and training a multiway classifier on these vectors. To this end, we introduce a novel vocabulary using dense color SIFT descriptors and then investigate the classification performance under changes in the size of the visual vocabulary, the number of latent topics learned, and the type of discriminative classifier used (k-nearest neighbor or SVM). We achieve superior classification performance to recent publications that have used a bag of visual word representation, in all cases, using the authors' own data sets and testing protocols. We also investigate the gain in adding spatial information. We show applications to image retrieval with relevance feedback and to scene classification in videos.}, author = {Bosch, A. and Zisserman, A. and Muoz, X.}, booktitle = {Pattern Analysis and Machine Intelligence, IEEE Transactions on}, citeulike-article-id = {3047363}, citeulike-linkout-0 = {http://dx.doi.org/10.1109/TPAMI.2007.70716}, citeulike-linkout-1 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4359337}, day = {04}, doi = {10.1109/TPAMI.2007.70716}, journal = {Pattern Analysis and Machine Intelligence, IEEE Transactions on}, keywords = {imageclassification, svm}, month = {April}, number = {4}, pages = {712--727}, posted-at = {2008-07-28 04:55:31}, priority = {2}, title = {Scene Classification Using a Hybrid Generative/Discriminative Approach}, url = {http://dx.doi.org/10.1109/TPAMI.2007.70716}, volume = {30}, year = {2008} }

TY - JOUR ID - citeulike:3047363 L3 - citeulike-article-id:3047363 N2 - We investigate whether dimensionality reduction using a latent generative model is beneficial for the task of weakly supervised scene classification. In detail, we are given a set of labeled images of scenes (for example, coast, forest, city, river, etc.), and our objective is to classify a new image into one of these categories. Our approach consists of first discovering latent ";topics"; using probabilistic Latent Semantic Analysis (pLSA), a generative model from the statistical text literature here applied to a bag of visual words representation for each image, and subsequently, training a multiway classifier on the topic distribution vector for each image. We compare this approach to that of representing each image by a bag of visual words vector directly and training a multiway classifier on these vectors. To this end, we introduce a novel vocabulary using dense color SIFT descriptors and then investigate the classification performance under changes in the size of the visual vocabulary, the number of latent topics learned, and the type of discriminative classifier used (k-nearest neighbor or SVM). We achieve superior classification performance to recent publications that have used a bag of visual word representation, in all cases, using the authors' own data sets and testing protocols. We also investigate the gain in adding spatial information. We show applications to image retrieval with relevance feedback and to scene classification in videos. IS - 4 JF - Pattern Analysis and Machine Intelligence, IEEE Transactions on EP - 727 TI - Scene Classification Using a Hybrid Generative/Discriminative Approach VL - 30 T2 - Pattern Analysis and Machine Intelligence, IEEE Transactions on SP - 712 KW - imageclassification KW - svm AU - Bosch, A AU - Zisserman, A AU - Muoz, X PY - 2008/04/04/ UR - http://dx.doi.org/10.1109/TPAMI.2007.70716 ER -