Supervised Auto-Encoding Twin-Bottleneck Hashing
This work addresses the problem of enhancing retrieval efficiency in high-dimensional data for applications like image or text search, but it is incremental as it builds upon an existing method.
The authors tackled the problem of improving deep hashing for approximate nearest neighbor search by generalizing an existing unsupervised method into a supervised network that incorporates label information and addresses class imbalance in multi-labeled datasets. The result was statistically significant improvement over the original model and competitive performance against other supervised methods on three datasets.
Deep hashing has shown to be a complexity-efficient solution for the Approximate Nearest Neighbor search problem in high dimensional space. Many methods usually build the loss function from pairwise or triplet data points to capture the local similarity structure. Other existing methods construct the similarity graph and consider all points simultaneously. Auto-encoding Twin-bottleneck Hashing is one such method that dynamically builds the graph. Specifically, each input data is encoded into a binary code and a continuous variable, or the so-called twin bottlenecks. The similarity graph is then computed from these binary codes, which get updated consistently during the training. In this work, we generalize the original model into a supervised deep hashing network by incorporating the label information. In addition, we examine the differences of codes structure between these two networks and consider the class imbalance problem especially in multi-labeled datasets. Experiments on three datasets yield statistically significant improvement against the original model. Results are also comparable and competitive to other supervised methods.