How Transferable are Reasoning Patterns in VQA?
How Transferable are Reasoning Patterns in VQA?
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 to detect and remove biases. …