按年被提到
20192019 · 2 次2026
视觉、语音与图像生成›卷积网络与图像识别·arXiv:1905.09272 · cs.CV

Data-Efficient Image Recognition with Contrastive Predictive Coding

Olivier J. Hénaff, Aravind Srinivas, Jeffrey De Fauw, Ali Razavi, Carl Doersch, S. M. Ali Eslami, Aaron van den Oord · 2019
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 3 人首次 2019-12-09 · 最近 2020-02-02
3不同的人
2活跃月份
3讨论串
1,072被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Human observers can learn to recognize new categories of images from a handful of examples, yet doing so with artificial ones remains an open challenge. We hypothesize that data-efficient recognition is enabled by representations which make the variability in natural signals more predictable. We therefore revisit and improve Contrastive Predictive Coding, an unsupervised objective for learning such representations. This new implementation produces features which support state-of-the-art linear classification accuracy on the ImageNet dataset. When used as input for non-linear classification with deep neural networks, this representation allows us to use 2-5x less labels than classifiers trained directly on image pixels. Finally, this unsupervised representation substantially improves transfer learning to object detection on the PASCAL VOC dataset, surpassing fully supervised pre-trained ImageNet classifiers.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论ankeshanand · 2020-02

“Sorry if it wasn't clear, I do mention the linear classification protocol several times in the post. If you want to evaluate performance on a classification task, you have to show it labels during evaluation, otherwise it's an impossible task. Note that the encoder is freezed during evaluation, and only a linear classifier is trained on top. Now, even whe…”

Contrastive Self-Supervised Learning原评论 ↗
被提交为 story · 2 次