基于语义输出码的Zero-Shot Learningzero-shot learning的目的是学习一个分类器 f:X\rightarrow Y ,分类器可以预测出训练集里遗漏缺失的新值。为此我们定义语义输出码分类器(semantic output code classifier(SOC…
We consider the problem of zero-shot learning, where the goal is to learn a clas- sifier f : X ! Y that must predict novel values of Y that were omitted from the training set. To achieve this, we define the notion of a semantic output code classifier (SOC) which utilizes a knowledg...
Hinton等在2009年的Zero-shot learning with semantic output codes这篇论文里,提到的语意输出编码方式,思想其实与DAP的思路类似,也是在之前的特征空间与标签之间增加了一层,这里增加的一层不再是数据本身的属性,而是标签本身的编码,说简单点就是NLP里面的词向量(word2vec),通过将标签进行词向量的编码,利用模型基于...
Hinton等在2009年的Zero-shot learning with semantic output codes这篇论文里,提到的语意输出编码方式,思想其实与DAP的思路类似,也是在之前的特征空间与标签之间增加了一层,这里增加的一层不再是数据本身的属性,而是标签本身的编码,说简单点就是NLP里面的词向量(word2vec),通过将标签进行词向量的编码,利用模型基于...
论文:Zero-Shot Learning with Semantic Output Codes We consider the problem of zero-shot learning, where the goal is to learn a classifierf:X→Yf:X→Y that must predict novel values of YY that were omitted from the training set. To achieve this, we define the notion of a semantic ...
Geoffrey E. Hinton, and Tom Michael Mitchell. Zero-shot learning with semantic output codes. In ...
Zero-shot learning with semantic output codes Advances in Neural Information Processing Systems (2009), pp. 1410-1418 View in ScopusGoogle Scholar [38] Rohrbach M., Stark M., Szarvas G., Gurevych I., Schiele B. What helps where–and why? semantic relatedness for knowledge transfer IEEE Conf...
3.2. GCN for Zero-shot Learning: 我们的模型是在 GCN 的基础上构建起来的,然而,不像是 entity classification,我们用一个 regression loss 来应用于 zero-shot recognition。我们框架的输入是:the set of categories and their corresponding semantic-embedding vectors。输出是:the visual classifier for each input...
Zero-shot learning with semantic output codes. In Proceedings of the Advances in Neural Information Processing Systems 22 (NIPS 2009), Vancouver, BC, Canada, 7–10 December 2009. [Google Scholar] Frome, A.; Corrado, G.S.; Shlens, J.; Bengio, S.; Dean, J.; Ranzato, M.; Mikolov, T...
[3] Larochelle H, Erhan D, Bengio Y. Zero-data learning of new tasks[C]//AAAI. 2008, 1(2): 3. [4] Palatucci M M, Pomerleau D A, Hinton G E, et al. Zero-shot learning with semantic output codes[J]. 2009. [5] Dosovitskiy A, Beyer L, Kolesnikov A, et al. An image is...