持续学习时任务构建至关重要：视觉问答的案例研究
Task Formulation Matters When Learning Continually: A Case Study in Visual Question Answering
AI总结：
本文以视觉问答为案例，比较三种持续学习任务构建方式，揭示输出分布变化、视觉嵌入与深层表示稳定性对性能、任务顺序敏感性及遗忘的影响。
摘要：
持续学习旨在让模型在一系列任务上进行增量训练，同时不遗忘先前知识。尽管持续学习已在计算机视觉领域得到广泛研究，但其在视觉+语言任务上的应用并不那么直接，因为相关设置可以根据输入模态以多种方式参数化。本文详细研究了不同设置如何影响视觉问答的性能。我们首先提出三种合理的任务构建方式，并展示它们对持续学习算法性能的影响。我们分解了任务相似性的若干因素，表明性能和对任务顺序的敏感性高度依赖于输出分布的变化。我们还研究了预训练模型的潜力，并比较了具有不同视觉嵌入的 transformer 模型的鲁棒性。最后，我们分析并解释了模型表示及其对遗忘的影响。结果突显了在更深层中稳定视觉表示的重要性。
英文摘要：
Continual learning aims to train a model incrementally on a sequence of tasks without forgetting previous knowledge. Although continual learning has been widely studied in computer vision, its application to Vision+Language tasks is not that straightforward, as settings can be parameterized in multiple ways according to their input modalities. In this paper, we present a detailed study of how different settings affect performance for Visual Question Answering. We first propose three plausible task formulations and demonstrate their impact on the performance of continual learning algorithms. We break down several factors of task similarity, showing that performance and sensitivity to task order highly depend on the shift of the output distribution. We also investigate the potential of pretrained models and compare the robustness of transformer models with different visual embeddings. Finally, we provide an analysis interpreting model representations and their impact on forgetting. Our results highlight the importance of stabilizing visual representations in deeper layers.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
