Single-Modal Entropy based Active Learning for Visual Question Answering

TL;DR

This paper introduces a novel active learning method for Visual Question Answering that leverages single-modal branches and mutual information to efficiently select informative samples, reducing labeling costs.

Contribution

It proposes a new single-modal entropy-based sample acquisition strategy, SMEM, combined with self-distillation for multi-modal VQA active learning, improving efficiency and performance.

Findings

Achieves state-of-the-art results on VQA datasets

Demonstrates cost-effective sample selection

Outperforms existing active learning baselines

Abstract

Constructing a large-scale labeled dataset in the real world, especially for high-level tasks (eg, Visual Question Answering), can be expensive and time-consuming. In addition, with the ever-growing amounts of data and architecture complexity, Active Learning has become an important aspect of computer vision research. In this work, we address Active Learning in the multi-modal setting of Visual Question Answering (VQA). In light of the multi-modal inputs, image and question, we propose a novel method for effective sample acquisition through the use of ad hoc single-modal branches for each input to leverage its information. Our mutual information based sample acquisition strategy Single-Modal Entropic Measure (SMEM) in addition to our self-distillation technique enables the sample acquisitor to exploit all present modalities and find the most informative samples. Our novel idea is simple to implement, cost-efficient, and readily adaptable to other multi-modal tasks. We confirm our findings on various VQA datasets through state-of-the-art performance by comparing to existing Active Learning baselines.