Hierarchical Average Precision Training for Pertinent Image Retrieval - Archive ouverte HAL Access content directly
Conference Papers Year : 2022

Hierarchical Average Precision Training for Pertinent Image Retrieval


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 code is publicly available at: https://github.com/elias-ramzi/HAPPIER.
Fichier principal
Vignette du fichier
eccv2022submission.pdf (7.73 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03712933 , version 1 (04-07-2022)
hal-03712933 , version 2 (21-07-2022)



Elias Ramzi, Nicolas Audebert, Nicolas Thome, Clément Rambour, Xavier Bitot. Hierarchical Average Precision Training for Pertinent Image Retrieval. ECCV 2022, Oct 2022, Tel-Aviv, Israel. ⟨hal-03712933v2⟩
311 View
72 Download



Gmail Facebook X LinkedIn More