Article Dans Une Revue IEEE Transactions on Pattern Analysis and Machine Intelligence Année : 2025

Optimization of Rank Losses for Image Retrieval

Résumé

In image retrieval, standard evaluation metrics rely on score ranking, e.g. average precision (AP), recall at k (R@k), normalized discounted cumulative gain (NDCG). In this work, we introduce a general framework for robust and decomposable rank losses optimization. It addresses two major challenges for end-to-end training of deep neural networks with rank losses: non-differentiability and non-decomposability. Firstly, we propose a general surrogate for ranking operator, SupRank, that is amenable to stochastic gradient descent. It provides an upperbound for rank losses and ensures robust training. Secondly, we use a simple yet effective loss function to reduce the decomposability gap between the averaged batch approximation of ranking losses and their values on the whole training set. We apply our framework to two standard metrics for image retrieval: AP and R@k. Additionally, we apply our framework to hierarchical image retrieval. We introduce an extension of AP, the hierarchical average precision H-AP, and optimize it as well as the NDCG. Finally, we create the first hierarchical landmarks retrieval dataset. We use a semi-automatic pipeline to create hierarchical labels, extending the large scale Google Landmarks v2 dataset. The hierarchical dataset is publicly available at github.com/cvdfoundation/google-landmark. Code is available at github.com/elias-ramzi/SupRank.

Fichier principal
Vignette du fichier
TPAMI_ROADMAP_HAPPIER.pdf (7.75 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-04975847 , version 1 (04-03-2025)

Licence

Identifiants

Citer

Elias Ramzi, Nicolas Audebert, Clément Rambour, André Araujo, Xavier Bitot, et al.. Optimization of Rank Losses for Image Retrieval. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025, pp.1-12. ⟨10.1109/TPAMI.2025.3543846⟩. ⟨hal-04975847⟩
237 Consultations
843 Téléchargements

Altmetric

Partager

  • More