Convolutional Hashing for Automated Scene Matching

02/09/2018
by   Martin Loncaric, et al.
0

We present a powerful new loss function and training scheme for learning binary hash functions. In particular, we demonstrate our method by creating for the first time a neural network that outperforms state-of-the-art Haar wavelets and color layout descriptors at the task of automated scene matching. By accurately relating distance on the manifold of network outputs to distance in Hamming space, we achieve a 100-fold reduction in nontrivial false positive rate and significantly higher true positive rate. We expect our insights to provide large wins for hashing models applied to other information retrieval hashing tasks as well.

READ FULL TEXT

page 1

page 5

research
10/01/2018

Learning Hash Codes via Hamming Distance Targets

We present a powerful new loss function and training scheme for learning...
research
10/31/2018

Non-Empty Bins with Simple Tabulation Hashing

We consider the hashing of a set X⊆ U with |X|=m using a simple tabulati...
research
05/21/2019

PDH : Probabilistic deep hashing based on MAP estimation of Hamming distance

With the growth of image on the web, research on hashing which enables h...
research
03/16/2021

Ternary Hashing

This paper proposes a novel ternary hash encoding for learning to hash m...
research
05/14/2018

NASH: Toward End-to-End Neural Architecture for Generative Semantic Hashing

Semantic hashing has become a powerful paradigm for fast similarity sear...
research
12/19/2013

Sparse similarity-preserving hashing

In recent years, a lot of attention has been devoted to efficient neares...
research
08/07/2021

OSCAR-Net: Object-centric Scene Graph Attention for Image Attribution

Images tell powerful stories but cannot always be trusted. Matching imag...

Please sign up or login with your details

Forgot password? Click here to reset