SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2102.07265 · 2021

Exploring Adversarial Robustness of Deep Metric Learning

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Deep Metric Learning (DML), a widely-used technique, involves learning a distance metric between pairs of samples. DML uses deep neural architectures to learn semantic embeddings of the input, where the distance between similar examples is small while dissimilar ones are far apart. Although the underlying neural networks produce good accuracy on naturally occurring samples, they are vulnerable to adversarially-perturbed samples that reduce performance. We take a first step towards training robust DML models and tackle the primary challenge of the metric losses being dependent on the samples in a mini-batch, unlike standard losses that only depend on the specific input-output pair. We analyze this dependence effect and contribute a robust optimization formulation. Using experiments on three commonly-used DML datasets, we demonstrate 5-76 fold increases in adversarial accuracy, and outperform an existing DML model that sought out to be robust.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2102.07265")
get_code_for_paper("2102.07265")
have("2102.07265")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2102.07265.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2102.07265.svg)](https://syntology.ai/paper/2102.07265)

Connect an agent — have() is free.