Sharing Matters for Generalization in Deep Metric Learning

04/12/2020
by   Timo Milbich, et al.
58

Learning the similarity between images constitutes the foundation for numerous vision tasks. The common paradigm is discriminative metric learning, which seeks an embedding that separates different training classes. However, the main challenge is to learn a metric that not only generalizes from training to novel, but related, test samples. It should also transfer to different object classes. So what complementary information is missed by the discriminative paradigm? Besides finding characteristics that separate between classes, we also need them to likely occur in novel categories, which is indicated if they are shared across training classes. This work investigates how to learn such characteristics without the need for extra annotations or training data. By formulating our approach as a novel triplet sampling strategy, it can be easily applied on top of recent ranking loss frameworks. Experiments show that, independent of the underlying network architecture and the specific ranking loss, our approach significantly improves performance in deep metric learning, leading to new the state-of-the-art results on various standard benchmark datasets.

READ FULL TEXT

page 3

page 4

page 11

page 12

research
04/28/2020

DiVA: Diverse Visual Feature Aggregation for Deep Metric Learning

Visual Similarity plays an important role in many computer vision applic...
research
09/25/2019

MIC: Mining Interclass Characteristics for Improved Metric Learning

Metric learning seeks to embed images of objects suchthat class-defined ...
research
04/28/2020

DiVA: Diverse Visual Feature Aggregation forDeep Metric Learning

Visual Similarity plays an important role in many computer vision applic...
research
10/16/2018

Deep Metric Learning with Hierarchical Triplet Loss

We present a novel hierarchical triplet loss (HTL) capable of automatica...
research
08/04/2020

Spherical Feature Transform for Deep Metric Learning

Data augmentation in feature space is effective to increase data diversi...
research
09/16/2019

Visualizing How Embeddings Generalize

Deep metric learning is often used to learn an embedding function that c...
research
10/09/2022

Coded Residual Transform for Generalizable Deep Metric Learning

A fundamental challenge in deep metric learning is the generalization ca...

Please sign up or login with your details

Forgot password? Click here to reset