Metric-based Regularization and Temporal Ensemble for Multi-task Learning using Heterogeneous Unsupervised Tasks

TL;DR

This paper introduces a novel multi-task learning framework using metric-based regularization and temporal ensemble techniques to learn generalized features from heterogeneous unsupervised tasks, improving performance across various target tasks.

Contribution

It proposes a new multi-task learning method with metric-based regularization and temporal task ensemble to reduce task bias and enhance feature generalization in unsupervised settings.

Findings

Outperforms state-of-the-art methods in classification, object detection, and clustering.

Effectively learns generalized features without task bias.

Improves target task performance using unsupervised multi-task learning.

Abstract

One of the ways to improve the performance of a target task is to learn the transfer of abundant knowledge of a pre-trained network. However, learning of the pre-trained network requires high computation capability and large-scale labeled dataset. To mitigate the burden of large-scale labeling, learning in un/self-supervised manner can be a solution. In addition, using unsupervised multi-task learning, a generalized feature representation can be learned. However, unsupervised multi-task learning can be biased to a specific task. To overcome this problem, we propose the metric-based regularization term and temporal task ensemble (TTE) for multi-task learning. Since these two techniques prevent the entire network from learning in a state deviated to a specific task, it is possible to learn a generalized feature representation that appropriately reflects the characteristics of each task without biasing. Experimental results for three target tasks such as classification, object detection and embedding clustering prove that the TTE-based multi-task framework is more effective than the state-of-the-art (SOTA) method in improving the performance of a target task.