English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Recent studies have shown that many deep metric learning loss functionsperform very similarly under the same experimental conditions. One potentialreason for this unexpected result is that all losses let the network focus onsimilar image regions or properties. In this paper, we investigate this byconducting a two-step analysis to extract and compare the learned visualfeatures of the same model architecture trained with different loss functions:First, we compare the learned features on the pixel level by correlatingsaliency maps of the same input images. Second, we compare the clustering ofembeddings for several image properties, e.g. object color or illumination. Toprovide independent control over these properties, photo-realistic 3D carrenders similar to images in the Cars196 dataset are generated. In ouranalysis, we compare 14 pretrained models from a recent study and find that,even though all models perform similarly, different loss functions can guidethe model to learn different features. We especially find differences betweenclassification and ranking based losses. Our analysis also shows that someseemingly irrelevant properties can have significant influence on the resultingembedding. We encourage researchers from the deep metric learning community touse our methods to get insights into the features learned by their proposedmethods.

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