Symmetrical Synthesis for Deep Metric Learning

01/31/2020
by   Geonmo Gu, et al.
0

Deep metric learning aims to learn embeddings that contain semantic similarity information among data points. To learn better embeddings, methods to generate synthetic hard samples have been proposed. Existing methods of synthetic hard sample generation are adopting autoencoders or generative adversarial networks, but this leads to more hyper-parameters, harder optimization, and slower training speed. In this paper, we address these problems by proposing a novel method of synthetic hard sample generation called symmetrical synthesis. Given two original feature points from the same class, the proposed method firstly generates synthetic points with each other as an axis of symmetry. Secondly, it performs hard negative pair mining within the original and synthetic points to select a more informative negative pair for computing the metric learning loss. Our proposed method is hyper-parameter free and plug-and-play for existing metric learning losses without network modification. We demonstrate the superiority of our proposed method over existing methods for a variety of loss functions on clustering and image retrieval tasks. Our implementations is publicly available.

READ FULL TEXT
research
03/05/2020

Embedding Expansion: Augmentation in Embedding Space for Deep Metric Learning

Learning the distance metric between pairs of samples has been studied f...
research
12/04/2021

Construct Informative Triplet with Two-stage Hard-sample Generation

In this paper, we propose a robust sample generation scheme to construct...
research
11/22/2019

Instance Cross Entropy for Deep Metric Learning

Loss functions play a crucial role in deep metric learning thus a variet...
research
08/20/2021

LoOp: Looking for Optimal Hard Negative Embeddings for Deep Metric Learning

Deep metric learning has been effectively used to learn distance metrics...
research
11/02/2016

Learning Deep Embeddings with Histogram Loss

We suggest a loss for learning deep embeddings. The new loss does not in...
research
06/11/2020

Improving Deep Metric Learning with Virtual Classes and Examples Mining

In deep metric learning, the training procedure relies on sampling infor...
research
07/17/2019

Deep Metric Learning with Alternating Projections onto Feasible Sets

During the training of networks for distance metric learning, minimizers...

Please sign up or login with your details

Forgot password? Click here to reset