Image Retrieval using Multi-scale CNN Features Pooling

04/21/2020
by   Federico Vaccaro, et al.
10

In this paper, we address the problem of image retrieval by learning images representation based on the activations of a Convolutional Neural Network. We present an end-to-end trainable network architecture that exploits a novel multi-scale local pooling based on NetVLAD and a triplet mining procedure based on samples difficulty to obtain an effective image representation. Extensive experiments show that our approach is able to reach state-of-the-art results on three standard datasets.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset