arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2010.06469cs.CVcs.LG
收藏

让每个标签都有价值:通过整合领域知识处理语义不精确

Making Every Label Count: Handling Semantic Imprecision by Integrating Domain Knowledge

Computer Vision Group Friedrich Schiller University Jena(耶拿弗里德里希·席勒大学计算机视觉组)

Clemens-Alexander Brust, Björn Barz, Joachim Denzler

摘要:

从网络上抓取或由志愿者(如Mechanical Turkers或公民科学家)提供的嘈杂数据被认为是专业标记数据的替代品。已经有研究专注于减轻标签噪音的影响。它通常被建模为不准确,其中正确的标签被来自同一集合的不正确标签替换。我们考虑标签噪声的另一个维度:不精确性。例如,非繁殖的雪鹀被标记为鸟类。这个标签是正确的,但不像任务要求的那样精确。标准的softmax分类器不能从这样一个弱标签中学习,因为它们认为所有的类都是互斥的,而非繁殖的雪鹀和鸟不是。我们提出了CHILLAX(Class Hierarchies for Imprecise Label Learning and Annotation eXtrapolation),这是一种基于层次分类的方法,可以充分利用任何精度的标签。在NABIrds和ILSVRC 2012的噪声变体上的实验表明,我们的方法比强基线高出16.4个百分点,比当前最先进的方法高出3.9个百分点。

英文摘要:

Noisy data, crawled from the web or supplied by volunteers such as Mechanical Turkers or citizen scientists, is considered an alternative to professionally labeled data. There has been research focused on mitigating the effects of label noise. It is typically modeled as inaccuracy, where the correct label is replaced by an incorrect label from the same set. We consider an additional dimension of label noise: imprecision. For example, a non-breeding snow bunting is labeled as a bird. This label is correct, but not as precise as the task requires. Standard softmax classifiers cannot learn from such a weak label because they consider all classes mutually exclusive, which non-breeding snow bunting and bird are not. We propose CHILLAX (Class Hierarchies for Imprecise Label Learning and Annotation eXtrapolation), a method based on hierarchical classification, to fully utilize labels of any precision. Experiments on noisy variants of NABirds and ILSVRC2012 show that our method outperforms strong baselines by as much as 16.4 percentage points, and the current state of the art by up to 3.9 percentage points.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑