Existing Visual Question Answering (VQA) methods tend to exploit dataset biases and spurious statistical correlations, instead of producing right answers for the right reasons. To address this issue, recent bias mitigation methods for VQA propose to incorporate visual cues (e.g., human attention maps) to better ground the VQA models, showcasing impressive gains. However, we show that the performance improvements are not a result of improved visual grounding, but a regularization effect which prevents over-fitting to linguistic priors. For instance, we find that it is not actually necessary to provide proper, human-based cues; random, insensible cues also result in similar improvements. Based on this observation, we propose a simpler regularization scheme that does not require any external annotations and yet achieves near state-of-the-art performance on VQA-CPv2.

We propose a new visual grounding task called Visual Query Detection (VQD). In VQD, the task is to localize a variable number of objects in an image where the objects are specified in natural language. VQD is related to visual referring expression comprehension, where the task is to localize only one object. We propose the first algorithms for VQD, and we evaluate them on both visual referring expression datasets and our new VQDv1 dataset.

Data augmentation is widely used to train deep neural networks for image classification tasks. Simply flipping images can help learning tremendously by increasing the number of training images by a factor of two. However, little work has been done studying data augmentation in natural language processing. Here, we describe two methods for data augmentation for Visual Question Answering (VQA). The first uses existing semantic annotations to generate new questions. The second method is a generative approach using recurrent neural networks. Experiments show that the proposed data augmentation improves performance of both baseline and state-of-the-art VQA algorithms.