Similarity Search in High Dimensions via Hashing
VLDB '99 Proceedings of the 25th International Conference on Very Large Data Bases
Fast Pose Estimation with Parameter-Sensitive Hashing
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
LIBLINEAR: A Library for Large Linear Classification
The Journal of Machine Learning Research
Performance evaluation of local colour invariants
Computer Vision and Image Understanding
Learning to Recognize Activities from the Wrong View Point
ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part I
International Journal of Approximate Reasoning
Efficient object category recognition using classemes
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part I
Product Quantization for Nearest Neighbor Search
IEEE Transactions on Pattern Analysis and Machine Intelligence
Interactively building a discriminative vocabulary of nameable attributes
CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
Discovering localized attributes for fine-grained recognition
CVPR '12 Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Scalable object-class retrieval with approximate and top-k ranking
ICCV '11 Proceedings of the 2011 International Conference on Computer Vision
Constrained semi-supervised learning using attributes and comparative attributes
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part III
Constrained semi-supervised learning using attributes and comparative attributes
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part III
Hi-index | 0.00 |
We present images with binary codes in a way that balances discrimination and learnability of the codes. In our method, each image claims its own code in a way that maintains discrimination while being predictable from visual data. Category memberships are usually good proxies for visual similarity but should not be enforced as a hard constraint. Our method learns codes that maximize separability of categories unless there is strong visual evidence against it. Simple linear SVMs can achieve state-of-the-art results with our short codes. In fact, our method produces state-of-the-art results on Caltech256 with only 128-dimensional bit vectors and outperforms state of the art by using longer codes. We also evaluate our method on ImageNet and show that our method outperforms state-of-the-art binary code methods on this large scale dataset. Lastly, our codes can discover a discriminative set of attributes.