AdaSin: Enhancing Hard Sample Metrics with Dual Adaptive Penalty for Face Recognition
This work addresses the challenge of effectively penalizing hard samples in face recognition, leading to improved feature discriminability, though it is incremental as it builds on existing margin-based and curriculum learning methods.
The paper tackles the problem of quantifying hard sample difficulty in face recognition by proposing the AdaSin loss function, which uses the sine of the angle between a sample's embedding and its class center as a metric and incorporates a dual adaptive penalty and curriculum learning, achieving superior accuracy on eight benchmarks.
In recent years, the emergence of deep convolutional neural networks has positioned face recognition as a prominent research focus in computer vision. Traditional loss functions, such as margin-based, hard-sample mining-based, and hybrid approaches, have achieved notable performance improvements, with some leveraging curriculum learning to optimize training. However, these methods often fall short in effectively quantifying the difficulty of hard samples. To address this, we propose Adaptive Sine (AdaSin) loss function, which introduces the sine of the angle between a sample's embedding feature and its ground-truth class center as a novel difficulty metric. This metric enables precise and effective penalization of hard samples. By incorporating curriculum learning, the model dynamically adjusts classification boundaries across different training stages. Unlike previous adaptive-margin loss functions, AdaSin introduce a dual adaptive penalty, applied to both the positive and negative cosine similarities of hard samples. This design imposes stronger constraints, enhancing intra-class compactness and inter-class separability. The combination of the dual adaptive penalty and curriculum learning is guided by a well-designed difficulty metric. It enables the model to focus more effectively on hard samples in later training stages, and lead to the extraction of highly discriminative face features. Extensive experiments across eight benchmarks demonstrate that AdaSin achieves superior accuracy compared to other state-of-the-art methods.