Label-Aware Ranked Loss for robust People Counting using Automotive in-cabin Radar

TL;DR

This paper proposes a novel Label-Aware Ranked loss function for robust regression in people counting using automotive in-cabin radar, improving accuracy over state-of-the-art methods.

Contribution

Introduction of the Label-Aware Ranked loss, a new metric loss that leverages label ordering for improved regression performance.

Findings

Achieves up to 83.0% accuracy in people counting

Neighboring labels accuracy reaches 99.9%

Outperforms state-of-the-art methods by 6.7% and 2.1%

Abstract

In this paper, we introduce the Label-Aware Ranked loss, a novel metric loss function. Compared to the state-of-the-art Deep Metric Learning losses, this function takes advantage of the ranked ordering of the labels in regression problems. To this end, we first show that the loss minimises when datapoints of different labels are ranked and laid at uniform angles between each other in the embedding space. Then, to measure its performance, we apply the proposed loss on a regression task of people counting with a short-range radar in a challenging scenario, namely a vehicle cabin. The introduced approach improves the accuracy as well as the neighboring labels accuracy up to 83.0% and 99.9%: An increase of 6.7%and 2.1% on state-of-the-art methods, respectively.