无需标注即可精准计数细分类别，如区分辣椒品种。
FiGO: Fine-Grained Object Counting without Annotations
- 用文本生成合成样本，通过正负样本损失学习细粒度概念嵌入。
- 在新数据集上显著超越基线，细粒度计数准确率提升超20%。
- 适合需要精确识别相似物种的农业、生态监测场景。
无标注类别无关计数（CAC）方法通过文本或视觉示例在测试时定义计数目标，降低标注成本。然而现有开放词汇方法在细粒度分类任务中表现不佳，如区分水禽种类或辣椒栽培品种。本文提出FiGO，一种仅需类别名称即可将通用计数模型适配至细粒度类别的新方法。该方法利用文本到图像扩散模型生成合成样本，并采用联合正样本与难负样本损失，学习紧凑的概念嵌入，进而驱动专用模块将任意冻结计数器输出转换为精准的细粒度估计。为评估细粒度计数能力，我们构建了LOOKALIKES数据集，包含14个父类下的37个子类别，每张图像含多个外观相似物体。FiGO显著优于强基线，使计数系统从“统计所有辣椒”跃升至“仅统计哈巴内罗辣椒”。
原文摘要 · Abstract (English)
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."
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。