Reducing Language Biases in Visual Question Answering with Visually-Grounded Question Encoder
This addresses the issue of biased VQA models for real-world applications, representing a novel method for a known bottleneck rather than an incremental improvement.
The paper tackled the problem of language biases in Visual Question Answering (VQA) models, which rely on train set priors like answering 'what sport is' as 'tennis', by proposing a Visually-Grounded Question Encoder (VGQE) that achieved state-of-the-art results on the bias-sensitive VQA-CPv2 dataset and improved accuracy on the standard VQAv2 benchmark.
Recent studies have shown that current VQA models are heavily biased on the language priors in the train set to answer the question, irrespective of the image. E.g., overwhelmingly answer "what sport is" as "tennis" or "what color banana" as "yellow." This behavior restricts them from real-world application scenarios. In this work, we propose a novel model-agnostic question encoder, Visually-Grounded Question Encoder (VGQE), for VQA that reduces this effect. VGQE utilizes both visual and language modalities equally while encoding the question. Hence the question representation itself gets sufficient visual-grounding, and thus reduces the dependency of the model on the language priors. We demonstrate the effect of VGQE on three recent VQA models and achieve state-of-the-art results on the bias-sensitive split of the VQAv2 dataset; VQA-CPv2. Further, unlike the existing bias-reduction techniques, on the standard VQAv2 benchmark, our approach does not drop the accuracy; instead, it improves the performance.