Learning With Average Precision: Training Image Retrieval With A Listwise Loss

Abstract

Image retrieval can be formulated as a ranking problem where the goal is to order database images by decreasing similarity to the query. Recent deep models for image retrieval have outperformed traditional methods by leveraging ranking-tailored loss functions, but important theoretical and practical problems remain. First, rather than directly optimizing the global ranking, they minimize an upper-bound on the essential loss, which does not necessarily result in an optimal mean average precision (mAP). Second, these methods require significant engineering efforts to work well, e.g. special pre-training and hard-negative mining. In this paper we propose instead to directly optimize the global mAP by leveraging recent advances in listwise loss formulations. Using a histogram binning approximation, the AP can be differentiated and thus employed to end-to-end learning. Compared to existing losses, the proposed method considers thousands of images simultaneously at each iteration and elimina

Stats

• citations326
• S2 citations—
• github stars0
• HF likes0
• heat score18.86
• arxiv keyrevaud2019learning

Related papers

• Optimization Of Rank Losses For Image Retrieval (2023)9.43
• Hierarchical Average Precision Training For Pertinent Image Retrieval (2022)9.10
• Robust And Decomposable Average Precision For Image Retrieval (2021)0.00
• Rethinking The Optimization Of Average Precision: Only Penalizing Negative Instances Before Positive Ones Is Enough (2021)11.00
• Smooth-ap: Smoothing The Path Towards Large-scale Image Retrieval (2020)15.06
• Not All Pairs Are Equal: Hierarchical Learning For Average-precision-oriented Video Retrieval (2024)7.50
• End-to-end Learning Of Deep Visual Representations For Image Retrieval (2016)19.66
• Optimizing Top Precision Performance Measure Of Content-based Image Retrieval By Learning Similarity Function (2016)9.59