Do Different Deep Metric Learning Losses Lead to Similar Learned Features?

by   Konstantin Kobs, et al.

Recent studies have shown that many deep metric learning loss functions perform very similarly under the same experimental conditions. One potential reason for this unexpected result is that all losses let the network focus on similar image regions or properties. In this paper, we investigate this by conducting a two-step analysis to extract and compare the learned visual features of the same model architecture trained with different loss functions: First, we compare the learned features on the pixel level by correlating saliency maps of the same input images. Second, we compare the clustering of embeddings for several image properties, e.g. object color or illumination. To provide independent control over these properties, photo-realistic 3D car renders similar to images in the Cars196 dataset are generated. In our analysis, we compare 14 pretrained models from a recent study and find that, even though all models perform similarly, different loss functions can guide the model to learn different features. We especially find differences between classification and ranking based losses. Our analysis also shows that some seemingly irrelevant properties can have significant influence on the resulting embedding. We encourage researchers from the deep metric learning community to use our methods to get insights into the features learned by their proposed methods.



There are no comments yet.


page 6

page 7

page 12

page 14

page 15

page 16

page 17

page 18


It Takes Two to Tango: Mixup for Deep Metric Learning

Metric learning involves learning a discriminative representation such t...

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

Deep Metric Learning (DML) learns a non-linear semantic embedding from i...

DIABLO: Dictionary-based Attention Block for Deep Metric Learning

Recent breakthroughs in representation learning of unseen classes and ex...

Deep Metric Learning with Spherical Embedding

Deep metric learning has attracted much attention in recent years, due t...

A Comparison of Metric Learning Loss Functions for End-To-End Speaker Verification

Despite the growing popularity of metric learning approaches, very littl...

Deep metric learning for multi-labelled radiographs

Many radiological studies can reveal the presence of several co-existing...

Multi-Head Deep Metric Learning Using Global and Local Representations

Deep Metric Learning (DML) models often require strong local and global ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.