In Defense of the Triplet Loss for Person Re-Identification

03/22/2017
by   Alexander Hermans, et al.
1

In the past few years, the field of computer vision has gone through a revolution fueled mainly by the advent of large datasets and the adoption of deep convolutional neural networks for end-to-end learning. The person re-identification subfield is no exception to this. Unfortunately, a prevailing belief in the community seems to be that the triplet loss is inferior to using surrogate losses (classification, verification) followed by a separate metric learning step. We show that, for models trained from scratch as well as pretrained ones, using a variant of the triplet loss to perform end-to-end deep metric learning outperforms most other published methods by a large margin.

READ FULL TEXT

page 1

page 11

page 12

page 13

page 14

page 15

10/02/2017

Margin Sample Mining Loss: A Deep Learning Based Method for Person Re-identification

Person re-identification (ReID) is an important task in computer vision....
01/12/2021

Learning Efficient Representations for Keyword Spotting with Triplet Loss

In the past few years, triplet loss-based metric embeddings have become ...
04/15/2016

DARI: Distance metric And Representation Integration for Person Verification

The past decade has witnessed the rapid development of feature represent...
06/16/2020

Visual Identification of Individual Holstein Friesian Cattle via Deep Metric Learning

Holstein Friesian cattle exhibit individually-characteristic black and w...
12/28/2020

Person Re-identification with Adversarial Triplet Embedding

Person re-identification is an important task and has widespread applica...
06/08/2020

Rethinking Classification Loss Designs for Person Re-identification with a Unified View

Person Re-identification (ReID) aims at matching a person of interest ac...