Embedding-aware generative model (EAGM) addresses the data insufficiency problem for zero-shot learning (ZSL) by constructing a generator between semantic and visual embedding spaces. Thanks to the predefined benchmark and protocols, the number of proposed EAGMs for ZSL is increasing rapidly. We argue that it is time to take a step back and reconsider the embedding-aware generative paradigm. The purpose of this paper is three-fold. First, given the fact that the current embedding features in benchmark datasets are somehow out-of-date, we improve the performance of EAGMs for ZSL remarkably with embarrassedly simple modifications on the embedding features. This is an important contribution, since the results reveal that the embedding of EAGMs deserves more attention. Second, we compare and analyze a significant number of EAGMs in depth. Based on five benchmark datasets, we update the state-of-the-art results for ZSL and give a strong baseline for few-shot learning (FSL), including the classic unseen-class few-shot learning (UFSL) and the more challenging seen-class few-shot learning (SFSL). Finally, a comprehensive generative model repository, namely, generative any-shot learning (GASL) repository, is provided, which contains the models, features, parameters, and settings of EAGMs for ZSL and FSL. Any results in this paper can be readily reproduced with only one command line based on GASL.
翻译:嵌入式基因模型(EAGM)通过在语义和视觉嵌入空间之间建造一个生成器,解决零点学习的数据不足问题。由于预先确定的基准和协议,ZSL的拟议EAGM数量正在迅速增加。我们认为,现在该是退一步,重新考虑嵌入式基因模型的时候了。本文件的目的是三重的。首先,鉴于基准数据集中目前嵌入的功能有些过时,我们明显改进了ZSL的EAGM性能,对嵌入功能进行了令人尴尬的简单修改。这是一个重要的贡献,因为结果显示,ERGM的嵌入需要更多关注。第二,我们比较和分析大量EAGM的深度。根据五个基准数据集,我们更新ZSL的先进结果,为基于少数点的学习提供一个强有力的基准(FSL),包括经典的隐蔽式微分数线学习模型(UFSL)和在IMISL的GSIS-GISM(GSL)中有一个具有挑战性的模型,一个GSISL,一个G-SL级的模型,一个GSIS-SIS-GSIS-inal-shima-shima-shima-shima-slevorma-Silma-ship-ship) 提供一个具有任何GISmainalmainalmasterlock。