论文标题
通过随机将类表示向量重新设计分类层
Redesigning the classification layer by randomizing the class representation vectors
论文作者
论文摘要
神经图像分类模型通常由两个组成部分组成。第一个是图像编码器，该图像负责将给定的原始图像编码为代表向量。第二个是分类组件，通常通过将代表向量投影到目标类向量来实现。估计目标类向量以及其他模型参数，以最大程度地减少损耗函数。在本文中，我们分析了分类层的简单设计选择如何影响学习动态。我们表明，标准的跨凝结训练隐含地捕获了不同类别之间的视觉相似性，这可能会恶化精度，甚至阻止某些模型融合。我们建议将类向量随机绘制，并将其设置为在训练过程中固定，从而使这些向量中编码的视觉相似性无效。我们分析了保持类向量固定的效果，并表明它可以提高类间的可分离性，阶层的紧凑性以及整体模型的准确性，同时保持对图像腐败的鲁棒性和学习概念的概括。
Neural image classification models typically consist of two components. The first is an image encoder, which is responsible for encoding a given raw image into a representative vector. The second is the classification component, which is often implemented by projecting the representative vector onto target class vectors. The target class vectors, along with the rest of the model parameters, are estimated so as to minimize the loss function. In this paper, we analyze how simple design choices for the classification layer affect the learning dynamics. We show that the standard cross-entropy training implicitly captures visual similarities between different classes, which might deteriorate accuracy or even prevents some models from converging. We propose to draw the class vectors randomly and set them as fixed during training, thus invalidating the visual similarities encoded in these vectors. We analyze the effects of keeping the class vectors fixed and show that it can increase the inter-class separability, intra-class compactness, and the overall model accuracy, while maintaining the robustness to image corruptions and the generalization of the learned concepts.
