用于深度神经网络背景偏差缓解的更快ISNet
Faster ISNet for Background Bias Mitigation on Deep Neural Networks
AI总结：
本文提出改进的ISNet架构，使训练时间与类别数无关，并引入模型无关的LRP实现，在背景偏差场景下超越现有模型，大幅提升训练速度。
摘要：
图像背景中的偏差或虚假相关性会影响神经网络，导致捷径学习（聪明汉斯效应）并阻碍对真实世界数据的泛化。最近提出的ISNet架构通过优化逐层相关性传播（LRP，一种解释技术）热力图，来减轻背景对深度分类器的影响。然而，ISNet的训练时间随应用中的类别数量线性增长。本文提出了重新设计的架构，使其训练时间不再依赖于类别数量。此外，我们引入了一种简洁且与模型无关的LRP实现。我们使用合成背景偏差和胸部X光片中的COVID-19检测（该应用通常存在背景偏差）对所提架构进行了挑战性验证。这些网络抑制了背景注意力和捷径学习，在分布外测试数据集上超越了多个最先进模型。所提架构相比ISNet可能带来巨大的训练速度提升，将LRP优化引入到原始模型无法实际处理的众多应用中。
英文摘要：
Bias or spurious correlations in image backgrounds can impact neural networks, causing shortcut learning (Clever Hans Effect) and hampering generalization to real-world data. ISNet, a recently introduced architecture, proposed the optimization of Layer-Wise Relevance Propagation (LRP, an explanation technique) heatmaps, to mitigate the influence of backgrounds on deep classifiers. However, ISNet's training time scales linearly with the number of classes in an application. Here, we propose reformulated architectures whose training time becomes independent from this number. Additionally, we introduce a concise and model-agnostic LRP implementation. We challenge the proposed architectures using synthetic background bias, and COVID-19 detection in chest X-rays, an application that commonly presents background bias. The networks hindered background attention and shortcut learning, surpassing multiple state-of-the-art models on out-of-distribution test datasets. Representing a potentially massive training speed improvement over ISNet, the proposed architectures introduce LRP optimization into a gamut of applications that the original model cannot feasibly handle.
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。
