Convolutional Hashing for Automated Scene Matching
This work addresses scene matching for information retrieval applications, offering substantial improvements over existing techniques.
The paper tackles the problem of automated scene matching by developing a new loss function and training scheme for learning binary hash functions, achieving a 100-fold reduction in nontrivial false positive rate and significantly higher true positive rate compared to state-of-the-art methods like Haar wavelets and color layout descriptors.
We present a powerful new loss function and training scheme for learning binary hash functions. In particular, we demonstrate our method by creating for the first time a neural network that outperforms state-of-the-art Haar wavelets and color layout descriptors at the task of automated scene matching. By accurately relating distance on the manifold of network outputs to distance in Hamming space, we achieve a 100-fold reduction in nontrivial false positive rate and significantly higher true positive rate. We expect our insights to provide large wins for hashing models applied to other information retrieval hashing tasks as well.