Skip to Main content Skip to Navigation
Conference papers

Robust and Decomposable Average Precision for Image Retrieval

Abstract : In image retrieval, standard evaluation metrics rely on score ranking, e.g. average precision (AP). In this paper, we introduce a method for robust and decomposable average precision (ROADMAP) addressing two major challenges for end-to-end training of deep neural networks with AP: non-differentiability and non-decomposability. Firstly, we propose a new differentiable approximation of the rank function, which provides an upper bound of the AP loss and ensures robust training. Secondly, we design a simple yet effective loss function to reduce the decomposability gap between the AP in the whole training set and its averaged batch approximation, for which we provide theoretical guarantees. Extensive experiments conducted on three image retrieval datasets show that ROADMAP outperforms several recent AP approximation methods and highlight the importance of our two contributions. Finally, using ROADMAP for training deep models yields very good performances, outperforming state-of-the-art results on the three datasets.
Complete list of metadata
Contributor : Elias Ramzi Connect in order to contact the contributor
Submitted on : Wednesday, December 1, 2021 - 2:41:01 PM
Last modification on : Wednesday, September 28, 2022 - 5:59:43 AM


Files produced by the author(s)


  • HAL Id : hal-03359605, version 3
  • ARXIV : 2110.01445



Elias Ramzi, Nicolas Thome, Clément Rambour, Nicolas Audebert, Xavier Bitot. Robust and Decomposable Average Precision for Image Retrieval. Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS 2021), Dec 2021, Sydney, Australia. ⟨hal-03359605v3⟩



Record views


Files downloads