We propose a novel framework called Semantics-Preserving Adversarial
Embedding Network (SP-AEN) for zero-shot visual recognition (ZSL), where test
images and their classes are both unseen during training. SP-AEN aims to tackle
the inherent problem --- semantic loss --- in the prevailing family of
embedding-based ZSL, where some semantics would be discarded during training if
they are non-discriminative for training classes, but could become critical for
recognizing test classes. Specifically, SP-AEN prevents the semantic loss by
introducing an independent visual-to-semantic space embedder which disentangles
the semantic space into two subspaces for the two arguably conflicting
objectives: classification and reconstruction. Through adversarial learning of
the two subspaces, SP-AEN can transfer the semantics from the reconstructive
subspace to the discriminative one, accomplishing the improved zero-shot
recognition of unseen classes. Comparing with prior works, SP-AEN can not only
improve classification but also generate photo-realistic images, demonstrating
the effectiveness of semantic preservation. On four popular benchmarks: CUB,
AWA, SUN and aPY, SP-AEN considerably outperforms other state-of-the-art
methods by an absolute performance difference of 12.2\%, 9.3\%, 4.0\%, and
3.6\% in terms of harmonic mean values

提出了一种称为 SP-AEN 的新框架，用于进行零样本视觉识别，其目的是解决嵌入式零样本学习中的语义丢失问题，通过对两个子空间的敌对学习来实现语义的转移和提高零样本识别能力。在基准测试中，相比其他最先进的方法，SP-AEN 不仅能提高分类性能，还能生成逼真的图像。（提高了 12.2％、9.3％、4.0％和 3.6％的综合平均值）