Google Research 发布 Agile Deliberation 框架，用边界样本调教主观图像分类器
Google AI Research Releases Agile Deliberation Framework for Gray-Area Image Classifiers
Google 出的这个框架能让分类器自己学着划清模糊概念的边界，实测 F1 涨了 10.5 分，做图像审核的可以看看。
Google Research 推出人机协同框架 Agile Deliberation，让用户通过逐张审阅边界图像来定义模糊的视觉概念。在 18 场实际测试会话中，基于 Gemini 的分类器 F1 分数比 zero-shot 提升 10.5 分。该框架面向主观性强的分类任务，如判断图像是否显得专业或是否属于某类风格。
Google AI Research Releases Agile Deliberation Framework for Gray-Area Image Classifiers
Google Research released Agile Deliberation, a human-in-the-loop framework that helps users define subjective visual concepts through borderline images. In 18 live sessions, it lifted Gemini-based classifier F1 by 10.5 points over zero-shot. The post Google AI Research Releases Agile Deliberation Framework for Gray-Area Image Classifiers appeared first on MarkTechPost .
- Google Research: Blog11-04 20:07原文
