In Defense of the Triplet Loss for Person Re-Identification

by   Alexander Hermans, et al.

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.


page 1

page 11

page 12

page 13

page 14

page 15


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

Person re-identification (ReID) is an important task in computer vision....

Learning Efficient Representations for Keyword Spotting with Triplet Loss

In the past few years, triplet loss-based metric embeddings have become ...

DARI: Distance metric And Representation Integration for Person Verification

The past decade has witnessed the rapid development of feature represent...

Visual Identification of Individual Holstein Friesian Cattle via Deep Metric Learning

Holstein Friesian cattle exhibit individually-characteristic black and w...

Person Re-identification with Adversarial Triplet Embedding

Person re-identification is an important task and has widespread applica...

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

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