AI RESEARCH
TPCL: Task Progressive Curriculum Learning for Robust Visual Question Answering
arXiv CS.LG
•
ArXi:2411.17292v2 Announce Type: replace-cross Visual Question Answering (VQA) systems are notoriously brittle under distribution shifts and data scarcity. While previous solutions-such as ensemble methods and data augmentation-can improve performance in isolation, they fail to generalise well across in-distribution (IID), out-of-distribution (OOD), and low-data settings simultaneously. We argue that this limitation stems from the suboptimal