Zero-shot learning (ZSL) aims to identify unseen classes with zero samples during training. Broadly speaking, present ZSL methods usually adopt class-level semantic labels and compare them with instance-level semantic predictions to infer unseen classes. However, we find that such existing models mostly produce imbalanced semantic predictions, i.e. these models could perform precisely for some semantics, but may not for others. To address the drawback, we aim to introduce an imbalanced learning framework into ZSL. However, we find that imbalanced ZSL has two unique challenges: (1) Its imbalanced predictions are highly correlated with the value of semantic labels rather than the number of samples as typically considered in the traditional imbalanced learning; (2) Different semantics follow quite different error distributions between classes. To mitigate these issues, we first formalize ZSL as an imbalanced regression problem which offers theoretical foundations to interpret how semantic labels lead to imbalanced semantic predictions. We then propose a re-weighted loss termed Re-balanced Mean-Squared Error (ReMSE), which tracks the mean and variance of error distributions, thus ensuring rebalanced learning across classes. As a major contribution, we conduct a series of analyses showing that ReMSE is theoretically well established. Extensive experiments demonstrate that the proposed method effectively alleviates the imbalance in semantic prediction and outperforms many state-of-the-art ZSL methods.
翻译:零点学习( ZSL) 旨在识别在训练期间没有样本的隐蔽班级。 广义地说, 目前的 ZSL 方法通常采用类级语义标签, 并将之与试级语义学预测值进行对比, 以推断隐蔽班级。 然而, 我们发现, 这些现有模型大多产生不平衡的语义学预测, 即这些模型可以对某些语义学进行精确的预测, 但对其他人来说则并非如此。 为解决缺陷, 我们的目标是在 ZSL 中引入一个不平衡的学习框架。 然而, 我们发现, 不平衡的 ZSL 方法有两个独特的挑战:(1) 其不平衡的预测与语义标签值高度相关, 而不是传统不平衡学习中通常考虑的样本数量相关。 但是, 我们发现, 不同的语义学模式在不同的班级之间产生非常不同的错误分布。 为了缓解这些问题, 我们首先将 ZSLSL 正式确定为一个不平衡的回归问题, 提供理论基础来解释语义性标签如何导致不平衡的语义学预测。 我们然后提出一个重新加权的损失, 称为重新平衡的错误( ReMSE) Asqulimalimalblationalislationalal adview add) 。 因此, 分析了一种变化方法, 。