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 m

Stats

• citations43
• S2 citations—
• github stars0
• HF likes0
• heat score12.33
• arxiv keyengilberge2019sodeep

Related papers

• Optimization Of Rank Losses For Image Retrieval (2023)9.43
• Recall@k Surrogate Loss With Large Batches And Similarity Mixup (2021)11.29
• Three Things To Know About Deep Metric Learning (2024)0.00
• An Attention-based Deep Net For Learning To Rank (2017)0.00
• Scalable Learning Of Non-decomposable Objectives (2016)0.00
• Deep Metric Learning Using Similarities From Nonlinear Rank Approximations (2019)2.26
• Smooth-ap: Smoothing The Path Towards Large-scale Image Retrieval (2020)15.06
• Hierarchical Proxy-based Loss For Deep Metric Learning (2021)10.85