One-Shot Learning of Object Categories
IEEE Transactions on Pattern Analysis and Machine Intelligence
Speeded-Up Robust Features (SURF)
Computer Vision and Image Understanding
Distance Metric Learning for Large Margin Nearest Neighbor Classification
The Journal of Machine Learning Research
Automatic attribute discovery and characterization from noisy web data
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part I
Extracting structures in image collections for object recognition
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part I
A discriminative latent model of object classes and attributes
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part V
The Journal of Machine Learning Research
ICANN'11 Proceedings of the 21th international conference on Artificial neural networks - Volume Part I
Interactively building a discriminative vocabulary of nameable attributes
CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
Baby talk: Understanding and generating simple image descriptions
CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
A joint learning framework for attribute models and object descriptions
ICCV '11 Proceedings of the 2011 International Conference on Computer Vision
Hi-index | 0.00 |
We propose a new learning method to infer a mid-level feature representation that combines the advantage of semantic attribute representations with the higher expressive power of non-semantic features. The idea lies in augmenting an existing attribute-based representation with additional dimensions for which an autoencoder model is coupled with a large-margin principle. This construction allows a smooth transition between the zero-shot regime with no training example, the unsupervised regime with training examples but without class labels, and the supervised regime with training examples and with class labels. The resulting optimization problem can be solved efficiently, because several of the necessity steps have closed-form solutions. Through extensive experiments we show that the augmented representation achieves better results in terms of object categorization accuracy than the semantic representation alone.