AutoencoderExisting embedding zero-shot learning models usually learn a projection function from the visual feature space to the semantic embedding space, e.g. attribute space or word vector space. However, the
Existing zero-shot learning (ZSL) models typically learn a projection function from a feature space to a semantic embedding space (e.g.~attribute space). However, such a projection function is only concerned with predicting the training seen class semantic representation (e.g.~attribute prediction...
论文题为《Semantic Autoencoder for Zero-Shot Learning》 论文主要提出了一种新的建立分类器算法:SAE(Semantic AutoEncoder),通过引入自编码器的结构较好解决了domain shift problem。 符号: X∈Rd∗N 代表d 维共N 个特征向量组成的矩阵,投影矩阵 W∈Rk∗d ,将特征向量投影到语义空间,得到latent representation...
Semantic Autoencoder for Zero-Shot Learning 模型会涉及到训练集和测试集的领域漂移(domainshift)问题。作者基于学习一个语义自编码器一定程度上解决了domainshift问题。整个文章最核心的算法是在自编码器进行编码和解码时,使用...SemanticAutoencoderforZero-ShotLearning[J].2017:4447-4456. [2]论文的代码GitHub:htt...
Semantic Autoencoder for Zero-Shot Learning,Elyor Kodirov Tao Xiang Shaogang Gong,Queen Mary University of London, UK,{e.kodirov, t.xiang, s.gong}@qmul.ac.uk 亮点 通过对耦学习提升零次学习系统的性能(类似CycleGan) 结构非常简洁,且可直接求解,速度非常快 ...
In this work, we present a novel solution to ZSL based on learning a Semantic AutoEncoder (SAE). Taking the encoder-decoder paradigm, an encoder aims to project a visual feature vector into the semantic space as in the existing ZSL models. However, the decoder exerts an additional constraint...
内容提示: Semantic Autoencoder for Zero-Shot LearningElyor Kodirov Tao Xiang Shaogang GongQueen Mary University of London, UK{e.kodirov, t.xiang, s.gong}@qmul.ac.ukAbstractExisting zero-shot learning (ZSL) models typically learna projection function from a feature space to a semantic em-...
[CVPR 2018 论文笔记] Preserving Semantic Relations for Zero-Shot Learning,程序员大本营,技术文章内容聚合第一站。
& Gong, S. Semantic autoencoder for zero-shot learning. IEEE. 1–10 (2017). Zhou, J., Ding, G. & Guo, Y. Latent semantic sparse hashing for cross-modal similarity search. ACM. 1–5 (2014). Wu, Y., Wang, S. & Huang, Q. Multi-modal semantic autoencoder for cross-modal ...