CNN Based Hashing for Image Retrieval
This work addresses the challenge of efficient image retrieval for web-scale data, but it is incremental as it builds on existing CNN and hashing techniques.
The paper tackled the problem of constructing similarity matrices for supervised hashing in image retrieval by proposing a CNN-based method that binarizes activations, achieving best performance on CIFAR-10 and comparable results on MNIST.
Along with data on the web increasing dramatically, hashing is becoming more and more popular as a method of approximate nearest neighbor search. Previous supervised hashing methods utilized similarity/dissimilarity matrix to get semantic information. But the matrix is not easy to construct for a new dataset. Rather than to reconstruct the matrix, we proposed a straightforward CNN-based hashing method, i.e. binarilizing the activations of a fully connected layer with threshold 0 and taking the binary result as hash codes. This method achieved the best performance on CIFAR-10 and was comparable with the state-of-the-art on MNIST. And our experiments on CIFAR-10 suggested that the signs of activations may carry more information than the relative values of activations between samples, and that the co-adaption between feature extractor and hash functions is important for hashing.