In Defense of the Triplet Loss for Person Re-Identification

Code

• github.com/layumi/Person_reID_baseline_pytorch
  pytorch★ 4,415
• github.com/OML-Team/open-metric-learning
  pytorch★ 985
• github.com/agongt408/vbranch
  tf★ 3
• github.com/bastiennNB/Pair_ReID
  pytorch★ 0
• github.com/immuno121/audio_source_classification
  pytorch★ 0
• github.com/cftang0827/pedestrian_recognition
  tf★ 0
• github.com/kilsenp/triplet-reid-pytorch
  pytorch★ 0
• github.com/zhengziqiang/ReshapeGAN
  tf★ 0
• github.com/AdrianUng/keras-triplet-loss-mnist
  tf★ 0
• github.com/thomas-liao/diva_tracking_reid
  tf★ 0

Abstract

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.

Tasks

Benchmark Results

Reproductions