An Analysis of Multi-Task Architectures for the Hierarchic Multi-Label Problem of Vehicle Model and Make Classification

TL;DR

This paper investigates how multi-task learning architectures can improve hierarchical vehicle make and model classification, demonstrating consistent performance gains across CNN and Transformer models on benchmark datasets.

Contribution

It provides a comprehensive analysis of parallel and cascaded multi-task architectures for hierarchical classification, highlighting their advantages and limitations.

Findings

Multi-task learning improves classification accuracy on benchmarks.

Both CNNs and Transformers benefit from multi-task approaches.

Significant performance gains observed on the CompCars dataset.

Abstract

Most information in our world is organized hierarchically; however, many Deep Learning approaches do not leverage this semantically rich structure. Research suggests that human learning benefits from exploiting the hierarchical structure of information, and intelligent models could similarly take advantage of this through multi-task learning. In this work, we analyze the advantages and limitations of multi-task learning in a hierarchical multi-label classification problem: car make and model classification. Considering both parallel and cascaded multi-task architectures, we evaluate their impact on different Deep Learning classifiers (CNNs, Transformers) while varying key factors such as dropout rate and loss weighting to gain deeper insight into the effectiveness of this approach. The tests are conducted on two established benchmarks: StanfordCars and CompCars. We observe the effectiveness of the multi-task paradigm on both datasets, improving the performance of the investigated CNN in almost all scenarios. Furthermore, the approach yields significant improvements on the CompCars dataset for both types of models.