Learning Compositional Representation for Few-shot Visual Question Answering
This addresses the challenge of few-shot learning in VQA for AI systems, enabling better adaptation to new categories with limited data, though it is incremental as it builds on existing VQA methods.
The paper tackles the problem of low accuracy in Visual Question Answering (VQA) for novel answer categories with few training examples by proposing an attribute network that extracts and composes attributes from well-represented answers to constrain learning for few-shot ones, achieving effectiveness demonstrated on the VQA v2.0 validation dataset.
Current methods of Visual Question Answering perform well on the answers with an amount of training data but have limited accuracy on the novel ones with few examples. However, humans can quickly adapt to these new categories with just a few glimpses, as they learn to organize the concepts that have been seen before to figure the novel class, which are hardly explored by the deep learning methods. Therefore, in this paper, we propose to extract the attributes from the answers with enough data, which are later composed to constrain the learning of the few-shot ones. We generate the few-shot dataset of VQA with a variety of answers and their attributes without any human effort. With this dataset, we build our attribute network to disentangle the attributes by learning their features from parts of the image instead of the whole one. Experimental results on the VQA v2.0 validation dataset demonstrate the effectiveness of our proposed attribute network and the constraint between answers and their corresponding attributes, as well as the ability of our method to handle the answers with few training examples.