Hierarchical Average Precision Training for Pertinent Image Retrieval

Elias Ramzi, Nicolas Audebert, Nicolas Thome, Clément Rambour, Xavier Bitot

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 (HAPPIER). HAPPIER is based on a new $$\mathcal {H}\text {-AP}$$ metric, which leverages a concept hierarchy to refine AP by integrating errors’ importance and better evaluate rankings. To train deep models with $$\mathcal {H}\text {-AP}$$ , 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 .