论文标题
从对抗性特征残留到紧凑的视觉功能的零射击学习
Zero-Shot Learning from Adversarial Feature Residual to Compact Visual Feature
论文作者
论文摘要
最近，许多零局学习（ZSL）方法着重于学习嵌入特征空间中的歧视对象特征，但是，这些方法学到的不看到级别特征的分布易于部分重叠，从而导致对象识别不准确。在解决这个问题时，我们提出了一个新型的对抗网络，以合成ZSL的紧凑型语义视觉特征，该特征由残留生成器，原型预测器和歧视器组成。残留生成器是生成视觉特征残差，该残留物与通过原型预测器预测的视觉原型集成，以合成视觉特征。鉴别因子是将合成视觉特征与从现有分类CNN提取的真实视觉特征区分开。由于生成的残差在数值上通常比所有原型之间的距离小得多，因此由建议的网络合成的不看到级别特征的分布较少。此外，考虑到分类CNN的视觉特征通常与其语义特征不一致，因此引入了一种简单的特征选择策略，以提取更紧凑的语义视觉特征。六个基准数据集的广泛实验结果表明，在大多数情况下，我们的方法可以比现有最新方法的性能明显高1.2-13.2％。
Recently, many zero-shot learning (ZSL) methods focused on learning discriminative object features in an embedding feature space, however, the distributions of the unseen-class features learned by these methods are prone to be partly overlapped, resulting in inaccurate object recognition. Addressing this problem, we propose a novel adversarial network to synthesize compact semantic visual features for ZSL, consisting of a residual generator, a prototype predictor, and a discriminator. The residual generator is to generate the visual feature residual, which is integrated with a visual prototype predicted via the prototype predictor for synthesizing the visual feature. The discriminator is to distinguish the synthetic visual features from the real ones extracted from an existing categorization CNN. Since the generated residuals are generally numerically much smaller than the distances among all the prototypes, the distributions of the unseen-class features synthesized by the proposed network are less overlapped. In addition, considering that the visual features from categorization CNNs are generally inconsistent with their semantic features, a simple feature selection strategy is introduced for extracting more compact semantic visual features. Extensive experimental results on six benchmark datasets demonstrate that our method could achieve a significantly better performance than existing state-of-the-art methods by 1.2-13.2% in most cases.
