Most image retrieval research focuses on improving predictive performance, but they may fall short in scenarios where the reliability of the prediction is crucial. Though uncertainty quantification can help by assessing uncertainty for query and database images, this method can provide only a heuristic estimate rather than an guarantee. To address these limitations, we present Risk Controlled Image Retrieval (RCIR), which generates retrieval sets that are guaranteed to contain the ground truth samples with a predefined probability. RCIR can be easily plugged into any image retrieval method, agnostic to data distribution and model selection. To the best of our knowledge, this is the first work that provides coverage guarantees for image retrieval. The validity and efficiency of RCIR is demonstrated on four real-world image retrieval datasets, including the Stanford CAR-196 (Krause et al. 2013), CUB-200 (Wah et al. 2011), the Pittsburgh dataset (Torii et al. 2013) and the ChestX-Det dataset (Lian et al. 2021).

翻译：大多数图像检索研究侧重于提升预测性能，但在预测可靠性至关重要的场景中，这些方法可能有所不足。尽管不确定性量化可通过评估查询图像与数据库图像的不确定性提供帮助，但该方法仅能提供启发式估计，而无法提供保证。为克服这些局限，我们提出了风险可控图像检索（Risk Controlled Image Retrieval, RCIR），该方法能够生成在预定义概率下保证包含真实样本的检索集合。RCIR可便捷地集成到任意图像检索方法中，且对数据分布与模型选择具有无偏性。据我们所知，这是首个为图像检索提供覆盖保证的研究工作。我们在四个真实世界图像检索数据集上验证了RCIR的有效性与高效性，包括Stanford CAR-196（Krause等，2013）、CUB-200（Wah等，2011）、Pittsburgh数据集（Torii等，2013）及ChestX-Det数据集（Lian等，2021）。