Dynamic Sampling for Deep Metric Learning

04/24/2020
by   Chang-Hui Liang, et al.
0

Deep metric learning maps visually similar images onto nearby locations and visually dissimilar images apart from each other in an embedding manifold. The learning process is mainly based on the supplied image negative and positive training pairs. In this paper, a dynamic sampling strategy is proposed to organize the training pairs in an easy-to-hard order to feed into the network. It allows the network to learn general boundaries between categories from the easy training pairs at its early stages and finalize the details of the model mainly relying on the hard training samples in the later. Compared to the existing training sample mining approaches, the hard samples are mined with little harm to the learned general model. This dynamic sampling strategy is formularized as two simple terms that are compatible with various loss functions. Consistent performance boost is observed when it is integrated with several popular loss functions on fashion search, fine-grained classification, and person re-identification tasks.

READ FULL TEXT
research
05/30/2019

The General Pair-based Weighting Loss for Deep Metric Learning

Deep metric learning aims at learning the distance metric between pair o...
research
04/08/2019

Improved Embeddings with Easy Positive Triplet Mining

Deep metric learning seeks to define an embedding where semantically sim...
research
07/30/2018

Hard-Aware Point-to-Set Deep Metric for Person Re-identification

Person re-identification (re-ID) is a highly challenging task due to lar...
research
06/09/2020

Reducing Class Collapse in Metric Learning with Easy Positive Sampling

Metric learning seeks perceptual embeddings where visually similar insta...
research
11/17/2016

Hard-Aware Deeply Cascaded Embedding

Riding on the waves of deep neural networks, deep metric learning has al...
research
01/16/2013

Regularized Discriminant Embedding for Visual Descriptor Learning

Images can vary according to changes in viewpoint, resolution, noise, an...
research
09/24/2019

Improving Collaborative Metric Learning with Efficient Negative Sampling

Distance metric learning based on triplet loss has been applied with suc...

Please sign up or login with your details

Forgot password? Click here to reset