Training products of experts by minimizing contrastive divergence
Neural Computation
Video Google: A Text Retrieval Approach to Object Matching in Videos
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Distinctive Image Features from Scale-Invariant Keypoints
International Journal of Computer Vision
CVPRW '04 Proceedings of the 2004 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'04) Volume 12 - Volume 12
Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
Supervised Learning of Quantizer Codebooks by Information Loss Minimization
IEEE Transactions on Pattern Analysis and Machine Intelligence
ICML '09 Proceedings of the 26th Annual International Conference on Machine Learning
International Journal of Approximate Reasoning
IEEE Transactions on Pattern Analysis and Machine Intelligence
Efficient highly over-complete sparse coding using a mixture model
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part V
Ask the locals: Multi-way local pooling for image recognition
ICCV '11 Proceedings of the 2011 International Conference on Computer Vision
ICCV '11 Proceedings of the 2011 International Conference on Computer Vision
A graph-matching kernel for object categorization
ICCV '11 Proceedings of the 2011 International Conference on Computer Vision
Pooling in image representation: The visual codeword point of view
Computer Vision and Image Understanding
Hi-index | 0.00 |
Recently, the coding of local features (e.g. SIFT) for image categorization tasks has been extensively studied. Incorporated within the Bag of Words (BoW) framework, these techniques optimize the projection of local features into the visual codebook, leading to state-of-the-art performances in many benchmark datasets. In this work, we propose a novel visual codebook learning approach using the restricted Boltzmann machine (RBM) as our generative model. Our contribution is three-fold. Firstly, we steer the unsupervised RBM learning using a regularization scheme, which decomposes into a combined prior for the sparsity of each feature's representation as well as the selectivity for each codeword. The codewords are then fine-tuned to be discriminative through the supervised learning from top-down labels. Secondly, we evaluate the proposed method with the Caltech-101 and 15-Scenes datasets, either matching or outperforming state-of-the-art results. The codebooks are compact and inference is fast. Finally, we introduce an original method to visualize the codebooks and decipher what each visual codeword encodes.