聚焦与扩展：通过输入特征的渐进操作进行训练指导
Focus-and-Expand: Training Guidance Through Gradual Manipulation of Input Features
摘要：
我们提出了一个简单而直观的焦点和扩展（\fax）的方法来指导神经网络的训练过程中的一个特定的解决方案。优化神经网络是一个高度非凸的问题。通常情况下，解决方案的空间很大，有许多可能的局部极小值，其中达到特定的最小值取决于许多因素。然而，在许多情况下，需要考虑输入的特定方面或特征的解决方案。例如，在存在偏差的情况下，忽略偏差特征的解决方案是更鲁棒和准确的解决方案。从参数连续方法中汲取灵感，我们建议通过输入域的逐渐变化，引导训练过程更多地考虑输入中的特定特征。\fax从每个输入数据点提取特征子集，并首先将学习器暴露给这些特征，将解决方案集中在它们上。然后，通过使用混合/混合参数$α$，它逐渐扩展学习过程以包括输入的所有特征。这个过程鼓励考虑所需的功能比其他更多。虽然不限于这一领域，我们定量评估我们的方法对各种计算机视觉任务的有效性，并实现了最先进的偏见消除，改进了现有的增强方法，并改进了图像分类任务的两个例子。通过这几个例子，我们展示了这种方法对各种问题的潜在影响，这些问题可以从理解解决方案中获益。
英文摘要：
We present a simple and intuitive Focus-and-eXpand (\fax) method to guide the training process of a neural network towards a specific solution. Optimizing a neural network is a highly non-convex problem. Typically, the space of solutions is large, with numerous possible local minima, where reaching a specific minimum depends on many factors. In many cases, however, a solution which considers specific aspects, or features, of the input is desired. For example, in the presence of bias, a solution that disregards the biased feature is a more robust and accurate one. Drawing inspiration from Parameter Continuation methods, we propose steering the training process to consider specific features in the input more than others, through gradual shifts in the input domain. \fax extracts a subset of features from each input data-point, and exposes the learner to these features first, Focusing the solution on them. Then, by using a blending/mixing parameter $α$ it gradually eXpands the learning process to include all features of the input. This process encourages the consideration of the desired features more than others. Though not restricted to this field, we quantitatively evaluate the effectiveness of our approach on various Computer Vision tasks, and achieve state-of-the-art bias removal, improvements to an established augmentation method, and two examples of improvements to image classification tasks. Through these few examples we demonstrate the impact this approach potentially carries for a wide variety of problems, which stand to gain from understanding the solution landscape.
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。
