免费的虚假相关性排序：一种基于目标检测的简单最后一层重训练框架
Spuriosity Rankings for Free: A Simple Framework for Last Layer Retraining Based on Object Detection
AI总结：
本文提出一种利用开放词汇目标检测对图像虚假程度进行自动排序的框架，无需人工监督即可筛选干净子集用于最后一层重训练，并在ImageNet-1k上验证了其有效性。
摘要：
深度神经网络在各个领域表现出卓越的性能。然而，这些模型对虚假特征的依赖引发了对其可靠性的担忧。针对这一问题，一种有前景的解决方案是最后一层重训练，即在一个不含虚假线索的小型数据子集上重新训练线性分类头。然而，选择该子集需要人工监督，这降低了其可扩展性。此外，所选子集中可能仍存在虚假线索。为解决这一问题，我们提出了一种新颖的排序框架，该框架利用开放词汇目标检测技术来识别不含虚假线索的图像。具体而言，我们使用目标检测器作为衡量图像中目标对象存在程度的评分工具。随后，根据该评分对图像进行排序，并在得分最高的数据子集上重新训练模型的最后一层。我们在ImageNet-1k数据集上的实验证明了该排序框架在基于虚假程度对图像进行排序以及将其用于最后一层重训练方面的有效性。
英文摘要：
Deep neural networks have exhibited remarkable performance in various domains. However, the reliance of these models on spurious features has raised concerns about their reliability. A promising solution to this problem is last-layer retraining, which involves retraining the linear classifier head on a small subset of data without spurious cues. Nevertheless, selecting this subset requires human supervision, which reduces its scalability. Moreover, spurious cues may still exist in the selected subset. As a solution to this problem, we propose a novel ranking framework that leverages an open vocabulary object detection technique to identify images without spurious cues. More specifically, we use the object detector as a measure to score the presence of the target object in the images. Next, the images are sorted based on this score, and the last-layer of the model is retrained on a subset of the data with the highest scores. Our experiments on the ImageNet-1k dataset demonstrate the effectiveness of this ranking framework in sorting images based on spuriousness and using them for last-layer retraining.
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。
