Timezone: »

An end-to-end approach for the verification problem: learning the right distance
Joao Monteiro · Isabela Albuquerque · Jahangir Alam · R Devon Hjelm · Tiago Falk

Tue Jul 14 08:00 AM -- 08:45 AM & Tue Jul 14 07:00 PM -- 07:45 PM (PDT) @ Virtual

In this contribution, we augment the metric learning setting by introducing a parametric pseudo-distance, trained jointly with the encoder. Several interpretations are thus drawn for the learned distance-like model's output. We first show it approximates a likelihood ratio which can be used for hypothesis tests, and that it further induces a large divergence across the joint distributions of pairs of examples from the same and from different classes. Evaluation is performed under the verification setting consisting of determining whether sets of examples belong to the same class, even if such classes are novel and were never presented to the model during training. Empirical evaluation shows such method defines an end-to-end approach for the verification problem, able to attain better performance than simple scorers such as those based on cosine similarity and further outperforming widely used downstream classifiers. We further observe training is much simplified under the proposed approach compared to metric learning with actual distances, requiring no complex scheme to harvest pairs of examples.

Author Information

Joao Monteiro (Institut National de la Recherche Scientifique (INRS))
Isabela Albuquerque (Institut National de la Recherche Scientifique)
Jahangir Alam (Computer Research Institute of Montreal (CRIM), Montreal (Quebec) Canada)
R Devon Hjelm (Microsoft Research)
Tiago Falk (INRS-EMT)

More from the Same Authors