论文标题
可逆的零射击识别流
Invertible Zero-Shot Recognition Flows
论文作者
论文摘要
最近，深层生成模型已成功地应用于零拍学习（ZSL）。但是，gan和vaes的基本缺点（例如，以ZSL为导向的正规化器和有限的生成质量的训练的硬度）阻碍了现有的生成ZSL模型完全绕过观察到的无人看见的偏见。为了解决上述局限性，这项工作将新的生成模型（即基于流的模型）纳入ZSL。提出的可逆零击流量（IZF）通过可逆流网络的正向通过学习分解的数据嵌入（即语义因素和非语义因素），而反向通行证会生成数据示例。从理论上讲，该过程将常规生成流动扩展到分解的条件方案。为了明确解决偏差问题，我们的模型扩大了基于基于样本的距离测量值的可见的无见分布差异。值得注意的是，IZF可以灵活地与天真的贝叶斯分类器或可训练的分类器一起使用，以零射击识别。在经典和广义设置中，对广泛预订的ZSL基准测试的实验证明了IZF的显着性能提高。
Deep generative models have been successfully applied to Zero-Shot Learning (ZSL) recently. However, the underlying drawbacks of GANs and VAEs (e.g., the hardness of training with ZSL-oriented regularizers and the limited generation quality) hinder the existing generative ZSL models from fully bypassing the seen-unseen bias. To tackle the above limitations, for the first time, this work incorporates a new family of generative models (i.e., flow-based models) into ZSL. The proposed Invertible Zero-shot Flow (IZF) learns factorized data embeddings (i.e., the semantic factors and the non-semantic ones) with the forward pass of an invertible flow network, while the reverse pass generates data samples. This procedure theoretically extends conventional generative flows to a factorized conditional scheme. To explicitly solve the bias problem, our model enlarges the seen-unseen distributional discrepancy based on negative sample-based distance measurement. Notably, IZF works flexibly with either a naive Bayesian classifier or a held-out trainable one for zero-shot recognition. Experiments on widely-adopted ZSL benchmarks demonstrate the significant performance gain of IZF over existing methods, in both classic and generalized settings.
