Risk Controlled Image Retrieval

Abstract

Most image retrieval research prioritizes improving predictive performance, often overlooking situations where the reliability of predictions is equally important. The gap between model performance and reliability requirements highlights the need for a systematic approach to analyze and address the risks associated with image retrieval. Uncertainty quantification technique can be applied to mitigate this issue by assessing uncertainty for retrieval sets, but it provides only a heuristic estimate of uncertainty rather than a guarantee. To address these limitations, we present Risk Controlled Image Retrieval (RCIR), which generates retrieval sets with coverage guarantee, i.e., retrieval sets that are guaranteed to contain the true nearest neighbors with a predefined probability. RCIR can be easily integrated with existing uncertainty-aware image retrieval systems, agnostic to data distribution and model selection. To the best of our knowledge, this is the first work that provides coverag

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keycai2023risk

Related papers

• Bayesian Triplet Loss: Uncertainty Quantification In Image Retrieval (2020)11.49
• Retrievalguard: Provably Robust 1-nearest Neighbor Image Retrieval (2022)0.00
• Reliability-aware Prediction Via Uncertainty Learning For Person Image Retrieval (2022)8.35
• Exploring Uncertainty Measures For Image-caption Embedding-and-retrieval Task (2019)2.26
• Heterogeneous Uncertainty-guided Composed Image Retrieval With Fine-grained Probabilistic Learning (2026)0.00
• Ranking-aware Uncertainty For Text-guided Image Retrieval (2023)0.00
• Exploring Uncertainty In Conditional Multi-modal Retrieval Systems (2019)0.00
• Qure: Query-relevant Retrieval Through Hard Negative Sampling In Composed Image Retrieval (2025)2.35