揭示VQA中视觉定位方法的全部潜力
Uncovering the Full Potential of Visual Grounding Methods in VQA
AI总结：
本研究指出VQA中VG方法评估因假设视觉信息可用性而存在缺陷，证明在纠正评估条件后这些方法能更加有效。
摘要：
VQA中的VG方法试图通过增强模型对问题相关视觉信息的依赖来提升VQA性能。训练和测试中通常假设视觉输入中存在此类相关信息。然而，在处理大规模VQA中常见的不完美图像表示时，这一假设存在根本缺陷，因为视觉特征所携带的信息经常偏离预期的真实内容。因此，VG方法的训练和测试主要在不准确的数据上进行，这阻碍了对其潜在益处的正确评估。在本研究中，我们证明当前VG方法的评估方案因对相关视觉信息可用性的错误假设而存在问题。实验表明，在纠正评估条件后，这些方法能更加有效。代码已在GitHub上提供。
英文摘要：
Visual Grounding (VG) methods in Visual Question Answering (VQA) attempt to improve VQA performance by strengthening a model's reliance on question-relevant visual information. The presence of such relevant information in the visual input is typically assumed in training and testing. This assumption, however, is inherently flawed when dealing with imperfect image representations common in large-scale VQA, where the information carried by visual features frequently deviates from expected ground-truth contents. As a result, training and testing of VG-methods is performed with largely inaccurate data, which obstructs proper assessment of their potential benefits. In this study, we demonstrate that current evaluation schemes for VG-methods are problematic due to the flawed assumption of availability of relevant visual information. Our experiments show that these methods can be much more effective when evaluation conditions are corrected. Code is provided on GitHub.
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。
