Timezone: »
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.Code and instructions to reproduce our results will be made publicly available at https://github.com/elias-ramzi/ROADMAP.
Author Information
Elias Ramzi (Conservatoire National des Arts et Métiers)
Nicolas THOME (Cnam (Conservatoire national des arts et métiers))
Clément Rambour (Cnam)
Nicolas Audebert (Conservatoire national des arts et métiers)
Xavier Bitot (Coexya)
More from the Same Authors
-
2020 Poster: Probabilistic Time Series Forecasting with Shape and Temporal Diversity »
Vincent LE GUEN · Nicolas THOME -
2019 Poster: Shape and Time Distortion Loss for Training Deep Time Series Forecasting Models »
Vincent LE GUEN · Nicolas THOME -
2019 Poster: Addressing Failure Prediction by Learning Model Confidence »
Charles Corbière · Nicolas THOME · Avner Bar-Hen · Matthieu Cord · Patrick Pérez -
2018 Poster: Revisiting Multi-Task Learning with ROCK: a Deep Residual Auxiliary Block for Visual Detection »
Taylor Mordan · Nicolas THOME · Gilles Henaff · Matthieu Cord