Enhanced Textual Feature Extraction for Visual Question Answering: A Simple Convolutional Approach
This work addresses the need for efficient VQA models for resource-limited settings, though it is incremental in nature.
The paper tackled the problem of improving textual feature extraction in Visual Question Answering (VQA) by comparing complex and simple models, finding that complex encoders are not always optimal, and proposed ConvGRU, which showed modest improvements on the VQA-v2 dataset for specific question types like Number and Count.
Visual Question Answering (VQA) has emerged as a highly engaging field in recent years, with increasing research focused on enhancing VQA accuracy through advanced models such as Transformers. Despite this growing interest, limited work has examined the comparative effectiveness of textual encoders in VQA, particularly considering model complexity and computational efficiency. In this work, we conduct a comprehensive comparison between complex textual models that leverage long-range dependencies and simpler models focusing on local textual features within a well-established VQA framework. Our findings reveal that employing complex textual encoders is not always the optimal approach for the VQA-v2 dataset. Motivated by this insight, we propose ConvGRU, a model that incorporates convolutional layers to improve text feature representation without substantially increasing model complexity. Tested on the VQA-v2 dataset, ConvGRU demonstrates a modest yet consistent improvement over baselines for question types such as Number and Count, which highlights the potential of lightweight architectures for VQA tasks, especially when computational resources are limited.