论文标题
使用分组的对抗性学习来解决零射门学习中的目标变化
Addressing target shift in zero-shot learning using grouped adversarial learning
论文作者
论文摘要
零光学习（ZSL）算法通常通过利用属性相关性来在看不见的类中进行预测来起作用。但是，在大多数实际环境中，这些相关性在测试时间并不能保持完整，并且这些相关性的变化会导致对零照片学习绩效的不利影响。在本文中，我们提出了一个针对ZSL的新范式，该范式：（i）利用不看到类的类属性映射来估计目标分布的变化（目标变化），（ii）提出了一种称为分组的对抗性学习（GAL）的新型技术来减少这种转移的负面影响。我们的方法广泛适用于几种现有的ZSL算法，包括具有隐式属性预测的算法。我们将提出的技术（$ g $ al）应用于三种流行的ZSL算法：ALE，SJE和DEAMISE，并在4个流行的ZSL数据集上显示性能改进：AWA2，APY，APY，Cub和Sun。我们在Sun和APY数据集上获得SOTA结果，并在AWA2上获得可比的结果。
Zero-shot learning (ZSL) algorithms typically work by exploiting attribute correlations to be able to make predictions in unseen classes. However, these correlations do not remain intact at test time in most practical settings and the resulting change in these correlations lead to adverse effects on zero-shot learning performance. In this paper, we present a new paradigm for ZSL that: (i) utilizes the class-attribute mapping of unseen classes to estimate the change in target distribution (target shift), and (ii) propose a novel technique called grouped Adversarial Learning (gAL) to reduce negative effects of this shift. Our approach is widely applicable for several existing ZSL algorithms, including those with implicit attribute predictions. We apply the proposed technique ($g$AL) on three popular ZSL algorithms: ALE, SJE, and DEVISE, and show performance improvements on 4 popular ZSL datasets: AwA2, aPY, CUB and SUN. We obtain SOTA results on SUN and aPY datasets and achieve comparable results on AwA2.
