Representation Learning with Contrastive Predictive Coding

  • 类型:arxiv
  • 标识:1807.03748
  • 链接:https://arxiv.org/abs/1807.03748
  • 主题:evaluation
  • 主分类:multimodal
  • 形态:method
  • 被引:14265
  • 被引来源:Semantic Scholar
  • S2被引:14265
  • OpenAlex被引:4549
  • 影响力被引:1577
  • TLDR:This work proposes a universal unsupervised learning approach to extract useful representations from high-dimensional data, which it calls Contrastive Predictive Coding, and demonstrates that the approach is able to learn useful representations achieving strong performance on four distinct domains: speech, images, text and reinforcement learning in 3D environments.
  • OpenAlex ID:W4297808394
  • OpenAlex DOI:10.48550/arxiv.1807.03748
  • DOI:10.48550/arxiv.1807.03748
  • DOI来源:OpenAlex
  • 开放获取:green
  • 开放获取链接:https://arxiv.org/pdf/1807.03748
  • OpenAlex更新:2026-08-25
  • 待LLM分类:否
  • 成熟度:production
  • 场景:contrastive learning、self-supervised、representation
  • 标题中文:基于对比预测编码的表征学习
  • TLDR中文:本文提出了一种通用的无监督学习方法——对比预测编码(Contrastive Predictive Coding),用于从高维数据中提取有用的表征,并在语音、图像、文本和 3D 环境中的强化学习四个不同领域取得了出色的性能。
  • 来源文件
  • [OpenAlex discover]
  • [S2 enrich]