SoDeep: a Sorting Deep net to learn ranking loss surrogates

Abstract : Several tasks in machine learning are evaluated using non-differentiable metrics such as mean average precision or Spearman correlation. However, their non-differentiability prevents from using them as objective functions in a learning framework. Surrogate and relaxation methods exist but tend to be specific to a given metric. In the present work, we introduce a new method to learn approximations of such non-differentiable objective functions. Our approach is based on a deep architecture that approximates the sorting of arbitrary sets of scores. It is trained virtually for free using synthetic data. This sorting deep (SoDeep) net can then be combined in a plug-and-play manner with existing deep architectures. We demonstrate the interest of our approach in three different tasks that require ranking: Cross-modal text-image retrieval, multi-label image classification and visual memorability ranking. Our approach yields very competitive results on these three tasks, which validates the merit and the flexibility of SoDeep as a proxy for sorting operation in ranking-based losses.
Complete list of metadatas

Cited literature [40 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02171870
Contributor : Martin Engilberge <>
Submitted on : Wednesday, July 3, 2019 - 11:28:51 AM
Last modification on : Wednesday, July 10, 2019 - 1:35:54 AM

File

cvpr2019.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02171870, version 1

Citation

Martin Engilberge, Louis Chevallier, Patrick Pérez, Matthieu Cord. SoDeep: a Sorting Deep net to learn ranking loss surrogates. CVPR 2019 - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Jun 2019, Long Beach, United States. ⟨hal-02171870⟩

Share

Metrics

Record views

14

Files downloads

12