Event ·Official first-hand

Google Research 发布 Agile Deliberation 框架，用边界样本调教主观图像分类器

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。

Current read

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。

2 sources31° AI heatLast updated 2026/11/5 05:42:18

Evidence

2 sources

Primary sourcemarktechpost

2026/11/5 05:42:18View source

Related source 1Google Research: Blog

2026/11/4 20:07:28View source

Conflict check

Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.

Open the story