通过随机化类表示向量重新设计分类层
Redesigning the classification layer by randomizing the class representation vectors
摘要:
神经图像分类模型通常由两个部分组成。第一个是图像编码器,负责将给定的原始图像编码为代表性矢量。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上来实现。估计目标类向量以及其余的模型参数,以便最小化损失函数。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。我们发现,标准的交叉熵训练隐式地捕获了不同类别之间的视觉相似性,这可能会降低准确性,甚至阻止某些模型收敛。我们建议随机绘制类向量,并在训练过程中将其设置为固定的,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,并表明它可以增加类间的可分性,类内的紧凑性和整体模型的准确性,同时保持对图像损坏和学习概念的泛化的鲁棒性。
英文摘要:
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.
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。