The paper introduces Dual Quality Margin Learning for Face Recognition (DQM‑Face), a framework that combines magnitude‑based and semantic quality estimation to refine attraction and repulsion dynamics during training. By integrating squeeze‑and‑excitation semantic attention with dual margins, the method enhances intra‑class compactness and inter‑class separation, yielding a more discriminative feature geometry. Experiments on challenging benchmarks show that DQM‑Face outperforms state‑of‑the‑art face recognition models and that the learned quality signal aligns well with recognition objectives.
By El Ouanas Belabbaci, Bhavesh Wani, Philipp Terh\"orst
arXiv:2607. 28936v1 Announce Type: cross Abstract: Facial biometric identification relies on the distinctiveness of user attributes within a high-dimensional embedding space.
By Omid Ahmadieh, Nima Karimian
Deep learning approaches to biometric verification are commonly trained by optimizing indirect objectives, creating a misalignment between the optimization process and the primary evaluation metric, typically the Equal Error Rate (EER). This paper introduces EERLoss: a subdifferentiable, arbitrarily accurate approximation to EER for training deep biometric models.
The paper argues that relying solely on zero‑shot task accuracy is insufficient for evaluating quantized large language models (LLMs) because accuracy ignores changes in the full predictive distribution. It proposes a distribution‑sensitive framework that measures fidelity loss by computing statistical distances—such as Jensen‑Shannon Divergence and Total Variation Distance—between the full‑vocabulary output distributions of a full‑precision BF16 reference and its quantized counterparts. Experiments across five foundation architectures and four reasoning benchmarks show that these divergence metrics increase with stronger quantization, revealing distributional drift that top‑1 accuracy fails to capture, and suggest that mixed‑precision Q4_K schemes can offer lower divergence than uniform Q4_0 at comparable memory usage.
By Shahzeb Qamar, Lorenz Sparrenberg, Christian Bauckhage, Baha Rababah, Carson Leung, Murat Kantarcioglu, Cuneyt Gurcan Akcora, Rafet Sifa
arXiv:2606. 24586v1 Announce Type: cross Abstract: Deep learning approaches to biometric verification are commonly trained by optimizing indirect objectives, creating a misalignment between the optimization process and the primary evaluation metric, typically the Equal Error Rate (EER).
By Nahuel Gonzalez, Marta Robledo-Moreno, Ivan DeAndres-Tame, Ruben Vera-Rodriguez, Ruben Tolosana
arXiv:2503. 08038v2 Announce Type: replace-cross Abstract: In this paper, we delve deeper into the Kullback-Leibler (KL) Divergence loss and mathematically prove that it is equivalent to the Decoupled Kullback-Leibler (DKL) Divergence loss that consists of (1) a weighted Mean Square Error (wMSE) loss and (2) a Cross-Entropy loss incorporating soft labels.
By Jiequan Cui, Beier Zhu, Qingshan Xu, Zhuotao Tian, Xiaojuan Qi, Bei Yu, Hanwang Zhang, Richang Hong
arXiv:2609.01014v1 Announce Type: new
Abstract: Low-quality face recognition (LQFR) remains challenging due to the difficulty of matching degraded query (probe) images against low-quality (LQ) enroll...
By Vedat Can Dilaver, Benjamin S. Riggan
DenseFace introduces a bias‑mitigation technique for face recognition that operates on pre‑trained models without retraining. It models each person’s face embeddings with a von Mises‑Fisher distribution and uses a density‑aware probabilistic matching procedure to account for demographic differences. Experiments show that DenseFace consistently reduces racial bias across various architectures and datasets while preserving recognition accuracy.
By Mansur Bultygov, Vadim Seliutin, Dmitry Nekhaev, Ivan Laptev
Low-quality face recognition (LQFR) remains challenging due to the difficulty of matching degraded query (probe) images against low-quality (LQ) enrollment (gallery) imagery and the scarcity of traini...
arXiv:2603. 21875v2 Announce Type: replace-cross Abstract: Speech deepfake source verification systems aims to determine whether two synthetic speech utterances originate from the same source generator, often assuming that the resulting source embeddings are independent of speaker traits.
By Xi Xuan, Wenxin Zhang, Zhiyu Li, Jennifer Williams, Ville Hautam\"aki, Tomi H. Kinnunen
arXiv:2606. 11505v1 Announce Type: cross Abstract: Biometric systems are increasingly deployed in security applications; however, they remain vulnerable to spoofing attacks, in which attackers exploit counterfeit biometric data to gain unauthorized access.
By Kumar Kartikey, Nikos Komninos
arXiv:2607. 14932v1 Announce Type: cross Abstract: Synthetic face datasets have become effective enough to train face recognition models with accuracy rivaling that of models trained on real photographs.
By Pawe{\l} Borsukiewicz, Daniele Lunghi, Wendk\^uuni C. Ou\'edraogo, Jacques Klein, Tegawend\'e F. Bissyand\'e