Hierarchical Average Precision Training For Pertinent Image Retrieval

Abstract

Image Retrieval is commonly evaluated with Average Precision (AP) or Recall@k. Yet, those metrics, are limited to binary labels and do not take into account errors' severity. This paper introduces a new hierarchical AP training method for pertinent image retrieval (HAP-PIER). HAPPIER is based on a new H-AP metric, which leverages a concept hierarchy to refine AP by integrating errors' importance and better evaluate rankings. To train deep models with H-AP, we carefully study the problem's structure and design a smooth lower bound surrogate combined with a clustering loss that ensures consistent ordering. Extensive experiments on 6 datasets show that HAPPIER significantly outperforms state-of-the-art methods for hierarchical retrieval, while being on par with the latest approaches when evaluating fine-grained ranking performances. Finally, we show that HAPPIER leads to better organization of the embedding space, and prevents most severe failure cases of non-hierarchical methods. Our cod

Stats

• citations6
• S2 citations—
• github stars23
• HF likes0
• heat score9.10
• arxiv keyramzi2022hierarchical

Related papers

• Learning With Average Precision: Training Image Retrieval With A Listwise Loss (2019)18.86
• Not All Pairs Are Equal: Hierarchical Learning For Average-precision-oriented Video Retrieval (2024)7.50
• Robust And Decomposable Average Precision For Image Retrieval (2021)0.00
• Smooth-ap: Smoothing The Path Towards Large-scale Image Retrieval (2020)15.06
• Optimization Of Rank Losses For Image Retrieval (2023)9.43
• Semantic Hierarchy Preserving Deep Hashing For Large-scale Image Retrieval (2019)5.24
• Mean Local Group Average Precision (mlgap): A New Performance Metric For Hashing-based Retrieval (2018)0.00
• Rethinking The Optimization Of Average Precision: Only Penalizing Negative Instances Before Positive Ones Is Enough (2021)11.00