3 accepted papers
Since its inception, Visual Question Answering (VQA) is notoriously known as a task, where models are prone to exploit biases in datasets to find shortcuts instead of performing high-level reasoning. Classical methods address this by removing biases from training data, or adding branches to models t…
Models for Visual Question Answering (VQA) are notorious for their tendency to rely on dataset biases, as the large and unbalanced diversity of questions and concepts involved and tends to prevent models from learning to ""reason"", leading them to perform ""educated guesses"" instead. In this paper…
Methods for Visual Question Anwering (VQA) are notorious for leveraging dataset biases rather than performing reasoning, hindering generalization. It has been recently shown that better reasoning patterns emerge in attention layers of a state-of-the-art VQA model when they are trained on perfect (or…