A Modulation Module for Multi-task Learning with Applications in Image Retrieval

TL;DR

This paper introduces a versatile modulation module for multi-task learning in convolutional neural networks, improving task relevance coupling and feature sharing, leading to better accuracy and efficiency in image retrieval tasks.

Contribution

A novel, end-to-end learnable modulation module that enhances multi-task learning by managing task relevance and feature sharing without task-specific design.

Findings

Improved accuracy in face and product retrieval tasks.

Enhanced storage efficiency compared to existing methods.

Effective handling of multiple tasks simultaneously.

Abstract

Multi-task learning has been widely adopted in many computer vision tasks to improve overall computation efficiency or boost the performance of individual tasks, under the assumption that those tasks are correlated and complementary to each other. However, the relationships between the tasks are complicated in practice, especially when the number of involved tasks scales up. When two tasks are of weak relevance, they may compete or even distract each other during joint training of shared parameters, and as a consequence undermine the learning of all the tasks. This will raise destructive interference which decreases learning efficiency of shared parameters and lead to low quality loss local optimum w.r.t. shared parameters. To address the this problem, we propose a general modulation module, which can be inserted into any convolutional neural network architecture, to encourage the coupling and feature sharing of relevant tasks while disentangling the learning of irrelevant tasks with minor parameters addition. Equipped with this module, gradient directions from different tasks can be enforced to be consistent for those shared parameters, which benefits multi-task joint training. The module is end-to-end learnable without ad-hoc design for specific tasks, and can naturally handle many tasks at the same time. We apply our approach on two retrieval tasks, face retrieval on the CelebA dataset [1] and product retrieval on the UT-Zappos50K dataset [2, 3], and demonstrate its advantage over other multi-task learning methods in both accuracy and storage efficiency.