PDH : Probabilistic deep hashing based on MAP estimation of Hamming distance
This addresses the need for more interpretable and efficient image retrieval systems, though it is incremental as it builds on existing deep hashing approaches.
The paper tackles the problem of tuning hyperparameters in deep hashing methods for image retrieval by deriving a single loss function from image probability distributions, enabling explainable hash codes without weight tuning. The result shows that the proposed method outperforms state-of-the-art hashing methods on datasets like MNIST, CIFAR-10, and SVHN.
With the growth of image on the web, research on hashing which enables high-speed image retrieval has been actively studied. In recent years, various hashing methods based on deep neural networks have been proposed and achieved higher precision than the other hashing methods. In these methods, multiple losses for hash codes and the parameters of neural networks are defined. They generate hash codes that minimize the weighted sum of the losses. Therefore, an expert has to tune the weights for the losses heuristically, and the probabilistic optimality of the loss function cannot be explained. In order to generate explainable hash codes without weight tuning, we theoretically derive a single loss function with no hyperparameters for the hash code from the probability distribution of the images. By generating hash codes that minimize this loss function, highly accurate image retrieval with probabilistic optimality is performed. We evaluate the performance of hashing using MNIST, CIFAR-10, SVHN and show that the proposed method outperforms the state-of-the-art hashing methods.