A Decidability-Based Loss Function
This work addresses the challenge of slow convergence and tricky parameter tuning in loss functions for biometric verification, offering a simpler alternative, though it appears incremental as it builds on existing loss function concepts.
The authors tackled the problem of improving embedding quality for biometric verification by proposing a new loss function based on the decidability index, which achieved competitive results on benchmarks like MNIST, Fashion-MNIST, CIFAR10, and CASIA-IrisV4 compared to existing methods.
Nowadays, deep learning is the standard approach for a wide range of problems, including biometrics, such as face recognition and speech recognition, etc. Biometric problems often use deep learning models to extract features from images, also known as embeddings. Moreover, the loss function used during training strongly influences the quality of the generated embeddings. In this work, a loss function based on the decidability index is proposed to improve the quality of embeddings for the verification routine. Our proposal, the D-loss, avoids some Triplet-based loss disadvantages such as the use of hard samples and tricky parameter tuning, which can lead to slow convergence. The proposed approach is compared against the Softmax (cross-entropy), Triplets Soft-Hard, and the Multi Similarity losses in four different benchmarks: MNIST, Fashion-MNIST, CIFAR10 and CASIA-IrisV4. The achieved results show the efficacy of the proposal when compared to other popular metrics in the literature. The D-loss computation, besides being simple, non-parametric and easy to implement, favors both the inter-class and intra-class scenarios.