CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition

TL;DR

CurricularFace introduces an adaptive curriculum learning loss for deep face recognition, dynamically emphasizing easy samples early on and hard samples later, leading to improved discriminability and superior performance on benchmarks.

Contribution

This work proposes a novel adaptive curriculum learning loss that adjusts sample importance during training, addressing limitations of prior methods in emphasizing hard samples.

Findings

Outperforms state-of-the-art methods on popular benchmarks.

Effectively balances easy and hard sample training stages.

Enhances discriminability in deep face recognition.

Abstract

As an emerging topic in face recognition, designing margin-based loss functions can increase the feature margin between different classes for enhanced discriminability. More recently, the idea of mining-based strategies is adopted to emphasize the misclassified samples, achieving promising results. However, during the entire training process, the prior methods either do not explicitly emphasize the sample based on its importance that renders the hard samples not fully exploited; or explicitly emphasize the effects of semi-hard/hard samples even at the early training stage that may lead to convergence issue. In this work, we propose a novel Adaptive Curriculum Learning loss (CurricularFace) that embeds the idea of curriculum learning into the loss function to achieve a novel training strategy for deep face recognition, which mainly addresses easy samples in the early training stage and hard ones in the later stage. Specifically, our CurricularFace adaptively adjusts the relative importance of easy and hard samples during different training stages. In each stage, different samples are assigned with different importance according to their corresponding difficultness. Extensive experimental results on popular benchmarks demonstrate the superiority of our CurricularFace over the state-of-the-art competitors.