Auto-JacoBin: Auto-encoder Jacobian Binary Hashing
This work addresses efficient storage and retrieval for large-scale data, but appears incremental as it builds on existing auto-encoder and hashing methods.
The paper tackled the problem of speeding up nearest neighbor search in large-scale datasets by proposing a robust auto-encoder model that preserves geometric relationships in Hamming space, achieving better than state-of-the-art results on three large-scale high-dimensional datasets.
Binary codes can be used to speed up nearest neighbor search tasks in large scale data sets as they are efficient for both storage and retrieval. In this paper, we propose a robust auto-encoder model that preserves the geometric relationships of high-dimensional data sets in Hamming space. This is done by considering a noise-removing function in a region surrounding the manifold where the training data points lie. This function is defined with the property that it projects the data points near the manifold into the manifold wisely, and we approximate this function by its first order approximation. Experimental results show that the proposed method achieves better than state-of-the-art results on three large scale high dimensional data sets.