feitianlzk的博客

《Handling Cold-Start Problem in Review Spam Detection by Jointly Embedding Texts and Behaviors》阅读笔记摘录

Reinforcement Learning for Relation Classification from Noisy Data阅读笔记

Opinion Spam DetectionProblemorigin: Positive opinions often mean profits and fames for businesses and individualslead to: promote or to discredit some target products, services, organizations, indi

源自Sebastian Ruder的博文The secret ingredients of word2vecQuestionsQ1. Are embeddings superior to distributional methods?With the right hyperparameters, no approach has a consistent advantage over

字体数据集 imagenet几个应用few shot classification (image) + RL + 推荐(cold start)

优先Few-shot Autoregressive Density Estimation: Towards Learning to Learn DistributionsMAMLSummary MAML: meta-learn an initial conditionLSTM optimization: meta-learn a good initial cond...

Transductive Unbiased Embedding for Zero-Shot LearningSummaryPROubias term: 在Loss添加一个针对未知类的loss, 部分抑制了zero shot天生倾向于带label数据的问题巧妙的数据利用，虽然target dataset没有用label(图片文字对应关系)，但是用了label的文字embedd...

Zero-Shot Visual Recognition using Semantics-Preserving Adversarial Embedding Networks收获多个网络如何组合? 相同目标collaborative, 不同目标adversarialtodo查看groud truth class embedding查看SAEConclusio...

Adversarial Learning for Semi-Supervised Semantic Segmentation本文核心要点如下SegNet as GeneratorDiscriminator: use a FCN(HxWxC -> HxWx1)Semi-supervised: 对于unlabeled data, adv loss, (fix D, maximi...