Deep Metric Learning with BIER: Boosting Independent Embeddings Robustly

01/15/2018
by   Michael Opitz, et al.
0

Learning similarity functions between image pairs with deep neural networks yields highly correlated activations of embeddings. In this work, we show how to improve the robustness of such embeddings by exploiting the independence within ensembles. To this end, we divide the last embedding layer of a deep network into an embedding ensemble and formulate training this ensemble as an online gradient boosting problem. Each learner receives a reweighted training sample from the previous learners. Further, we propose two loss functions which increase the diversity in our ensemble. These loss functions can be applied either for weight initialization or during training. Together, our contributions leverage large embedding sizes more effectively by significantly reducing correlation of the embedding and consequently increase retrieval accuracy of the embedding. Our method works with any differentiable loss function and does not introduce any additional parameters during test time. We evaluate our metric learning method on image retrieval tasks and show that it improves over state-of-the-art methods on the CUB 200-2011, Cars-196, Stanford Online Products, In-Shop Clothes Retrieval and VehicleID datasets.

READ FULL TEXT

page 14

page 17

page 18

page 19

page 20

research
04/02/2018

Attention-based Ensemble for Deep Metric Learning

Recently, ensemble has been applied to deep metric learning to yield sta...
research
08/13/2018

Deep Randomized Ensembles for Metric Learning

Learning embedding functions, which map semantically related inputs to n...
research
04/08/2019

Improved Embeddings with Easy Positive Triplet Mining

Deep metric learning seeks to define an embedding where semantically sim...
research
12/01/2019

The Group Loss for Deep Metric Learning

Deep metric learning has yielded impressive results in tasks such as clu...
research
04/07/2019

Learning Metrics from Teachers: Compact Networks for Image Embedding

Metric learning networks are used to compute image embeddings, which are...
research
07/02/2021

Ensemble of Loss Functions to Improve Generalizability of Deep Metric Learning methods

Deep Metric Learning (DML) learns a non-linear semantic embedding from i...
research
10/04/2022

On Background Bias in Deep Metric Learning

Deep Metric Learning trains a neural network to map input images to a lo...

Please sign up or login with your details

Forgot password? Click here to reset