Global S&T Development Trend Analysis Platform of Resources and Environment
DOI | 10.1126/science.aag2612 |
A generative vision model that trains with high data efficiency and breaks text-based CAPTCHAs | |
George, Dileep; Lehrach, Wolfgang; Kansky, Ken; Lazaro-Gredilla, Miguel; Laan, Christopher; Marthi, Bhaskara; Lou, Xinghua; Meng, Zhaoshi; Liu, Yi; Wang, Huayan; Lavin, Alex; Phoenix, D. Scott | |
2017-12-08 | |
发表期刊 | SCIENCE
![]() |
ISSN | 0036-8075 |
EISSN | 1095-9203 |
出版年 | 2017 |
卷号 | 358期号:6368 |
文章类型 | Article |
语种 | 英语 |
国家 | USA |
英文摘要 | Learning from a few examples and generalizing to markedly different situations are capabilities of human visual intelligence that are yet to be matched by leading machine learning models. By drawing inspiration from systems neuroscience, we introduce a probabilistic generative model for vision in which message-passing-based inference handles recognition, segmentation, and reasoning in a unified way. The model demonstrates excellent generalization and occlusion-reasoning capabilities and outperforms deep neural networks on a challenging scene text recognition benchmark while being 300-fold more data efficient. In addition, the model fundamentally breaks the defense of modern text-based CAPTCHAs (Completely Automated Public Turing test to tell Computers and Humans Apart) by generatively segmenting characters without CAPTCHA-specific heuristics. Our model emphasizes aspects such as data efficiency and compositionality that may be important in the path toward general artificial intelligence. |
领域 | 地球科学 ; 气候变化 ; 资源环境 |
收录类别 | SCI-E |
WOS记录号 | WOS:000417254700051 |
WOS关键词 | PRIMARY VISUAL-CORTEX ; OBJECT RECOGNITION ; SEGMENTATION ; ATTENTION |
WOS类目 | Multidisciplinary Sciences |
WOS研究方向 | Science & Technology - Other Topics |
URL | 查看原文 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://119.78.100.173/C666/handle/2XK7JSWQ/197504 |
专题 | 地球科学 资源环境科学 气候变化 |
作者单位 | Vicarious AI, 2 Union Sq, Union, CA 94587 USA |
推荐引用方式 GB/T 7714 | George, Dileep,Lehrach, Wolfgang,Kansky, Ken,et al. A generative vision model that trains with high data efficiency and breaks text-based CAPTCHAs[J]. SCIENCE,2017,358(6368). |
APA | George, Dileep.,Lehrach, Wolfgang.,Kansky, Ken.,Lazaro-Gredilla, Miguel.,Laan, Christopher.,...&Phoenix, D. Scott.(2017).A generative vision model that trains with high data efficiency and breaks text-based CAPTCHAs.SCIENCE,358(6368). |
MLA | George, Dileep,et al."A generative vision model that trains with high data efficiency and breaks text-based CAPTCHAs".SCIENCE 358.6368(2017). |
条目包含的文件 | 条目无相关文件。 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论