FiGO：无需标注的细粒度物体计数
FiGO: Fine-Grained Object Counting without Annotations
AI总结：
FiGO是一种无需标注的细粒度物体计数方法，通过生成合成示例和学习紧凑概念嵌入，实现对细粒度类别的准确计数。
摘要：
类无关计数（CAC）方法通过允许用户在测试时通过文本或视觉示例定义要计数的内容来降低标注成本。然而，当前的开放词汇方法在广义类别上表现良好，但在需要细粒度类别区分时会失败，例如区分水禽种类或辣椒品种。我们提出了FiGO，一种新的无标注方法，仅使用类别名称即可将现有计数模型适应到细粒度类别。我们的方法利用文本到图像扩散模型生成合成示例，并使用联合正/难负损失学习一个紧凑的概念嵌入，该嵌入条件化一个专门模块，将任何冻结的计数器输出转换为准确的细粒度估计。为了评估细粒度计数，我们引入了LOOKALIKES数据集，包含14个父类别下的37个子类别，每张图像中有很多视觉相似的物体。我们的方法显著优于强大的开放词汇基线，将计数系统从“计数所有辣椒”转变为“仅计数哈瓦那辣椒。”
英文摘要：
Class-agnostic counting (CAC) methods reduce annotation costs by letting users define what to count at test-time through text or visual exemplars. However, current open-vocabulary approaches work well for broad categories but fail when fine-grained category distinctions are needed, such as telling apart waterfowl species or pepper cultivars. We present FiGO, a new annotation-free method that adapts existing counting models to fine-grained categories using only the category name. Our approach uses a text-to-image diffusion model to create synthetic examples and a joint positive/hard-negative loss to learn a compact concept embedding that conditions a specialization module to convert outputs from any frozen counter into accurate, fine-grained estimates. To evaluate fine-grained counting, we introduce LOOKALIKES, a dataset of 37 subcategories across 14 parent categories with many visually similar objects per image. Our method substantially outperforms strong open-vocabulary baselines, moving counting systems from "count all the peppers" to "count only the habaneros."
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。
