Enhance Feature Discrimination for Unsupervised Hashing
This work addresses the challenge of feature discrimination in unsupervised hashing for applications like image retrieval, but it appears incremental as it builds upon existing methods.
The paper tackles the problem of improving feature discrimination in unsupervised hashing by proposing Gaussian Mixture Model embedding (Gemb), which enhances feature discriminative properties before hashing. The method boosts the performance of state-of-the-art hashing techniques like Binary Autoencoder and Iterative Quantization on three benchmark datasets.
We introduce a novel approach to improve unsupervised hashing. Specifically, we propose a very efficient embedding method: Gaussian Mixture Model embedding (Gemb). The proposed method, using Gaussian Mixture Model, embeds feature vector into a low-dimensional vector and, simultaneously, enhances the discriminative property of features before passing them into hashing. Our experiment shows that the proposed method boosts the hashing performance of many state-of-the-art, e.g. Binary Autoencoder (BA) [1], Iterative Quantization (ITQ) [2], in standard evaluation metrics for the three main benchmark datasets.