Mixup-based Deep Metric Learning Approaches for Incomplete Supervision

04/28/2022
by   Luiz H. Buris, et al.
0

Deep learning architectures have achieved promising results in different areas (e.g., medicine, agriculture, and security). However, using those powerful techniques in many real applications becomes challenging due to the large labeled collections required during training. Several works have pursued solutions to overcome it by proposing strategies that can learn more for less, e.g., weakly and semi-supervised learning approaches. As these approaches do not usually address memorization and sensitivity to adversarial examples, this paper presents three deep metric learning approaches combined with Mixup for incomplete-supervision scenarios. We show that some state-of-the-art approaches in metric learning might not work well in such scenarios. Moreover, the proposed approaches outperform most of them in different datasets.

READ FULL TEXT
research
02/27/2020

Affinity guided Geometric Semi-Supervised Metric Learning

In this paper, we address the semi-supervised metric learning problem, w...
research
05/10/2021

Semi-Supervised Metric Learning: A Deep Resurrection

Distance Metric Learning (DML) seeks to learn a discriminative embedding...
research
05/06/2020

Deep Divergence Learning

Classical linear metric learning methods have recently been extended alo...
research
04/29/2020

Metric learning by Similarity Network for Deep Semi-Supervised Learning

Deep semi-supervised learning has been widely implemented in the real-wo...
research
01/07/2021

Metric Learning for Session-based Recommendations

Session-based recommenders, used for making predictions out of users' un...
research
03/19/2020

Detecting Deepfakes with Metric Learning

With the arrival of several face-swapping applications such as FaceApp, ...
research
05/12/2022

Accounting for the Sequential Nature of States to Learn Features for Reinforcement Learning

In this work, we investigate the properties of data that cause popular r...

Please sign up or login with your details

Forgot password? Click here to reset