# xCos: An Explainable Cosine Metric for Face Verification Task

arXiv: https://arxiv.org/abs/2003.05383 · HTML: https://mlsanity.com/paper/2003.05383/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Mar 2020.

## Built on by (most cited first, 24 of 24)

- [Inversion-Based Style Transfer with Diffusion Models](https://mlsanity.com/paper/2211.13203/) (2022)
- [Explainable Model-Agnostic Similarity and Confidence in Face Verification](https://mlsanity.com/paper/2211.13735/) (2022)
- [Efficient Explainable Face Verification based on Similarity Score Argument Backpropagation](https://mlsanity.com/paper/2304.13409/) (2023)
- [Towards Visual Saliency Explanations of Face Verification](https://mlsanity.com/paper/2305.08546/) (2023)
- [SlerpFace: Face Template Protection via Spherical Linear Interpolation](https://mlsanity.com/paper/2407.03043/) (2024)
- [Explainable Face Verification via Feature-Guided Gradient Backpropagation](https://mlsanity.com/paper/2403.04549/) (2024)
- [A novel Facial Recognition technique with Focusing on Masked Faces](https://mlsanity.com/paper/2501.04444/) (2025)
- [Attributes Shape the Embedding Space of Face Recognition Models](https://mlsanity.com/paper/2507.11372/) (2025)
- [Explanation of Face Recognition via Saliency Maps](https://mlsanity.com/paper/2304.06118/) (2023)
- [Discriminative Deep Feature Visualization for Explainable Face Recognition](https://mlsanity.com/paper/2306.00402/) (2023)
- [Beyond Spatial Explanations: Explainable Face Recognition in the Frequency Domain](https://mlsanity.com/paper/2407.11941/) (2024)
- [Activation Template Matching Loss for Explainable Face Recognition](https://mlsanity.com/paper/2207.02179/) (2022)
- [Explaining Cross-Domain Recognition with Interpretable Deep Classifier](https://mlsanity.com/paper/2211.08249/) (2022)
- [A Survey on Interpretability in Visual Recognition](https://mlsanity.com/paper/2507.11099/) (2025)
- [Towards A Comprehensive Visual Saliency Explanation Framework for AI-based Face Recognition Systems](https://mlsanity.com/paper/2407.05983/) (2024)
- [Edge Enhanced Image Style Transfer via Transformers](https://mlsanity.com/paper/2301.00592/) (2023)
- [SASMU: boost the performance of generalized recognition model using synthetic face dataset](https://mlsanity.com/paper/2306.01449/) (2023)
- [Aligning Characteristic Descriptors with Images for Human-Expert-like Explainability](https://mlsanity.com/paper/2411.04008/) (2024)
- [Unsupervised Domain Adaptation with Dynamic Clustering and Contrastive Refinement for Gait Recognition](https://mlsanity.com/paper/2501.16608/) (2025)
- [Restricted Receptive Fields for Face Verification](https://mlsanity.com/paper/2510.10753/) (2025)
- [PLGSA-Transformer: Periocular Landmark-Guided Attention with Occlusion-Adaptive Cosine Thresholding for Cross-Modal Masked and Unmasked Face Recognition](https://mlsanity.com/paper/2607.03581/) (2026)
- [Explaining Image Similarity with Automatically Extracted Concept Activation Vectors](https://mlsanity.com/paper/2607.28386/) (2026)
- [EXPL-FR: Explaining Face Recognition Models via Vision-Language Alignment](https://mlsanity.com/paper/2608.21486/) (2026)
- [Benchmarking the Explanatory Quality of Open-Weight Vision-Language Models in Face Recognition](https://mlsanity.com/paper/2609.21879/) (2026)

## Abstract (arXiv)

We study the XAI (explainable AI) on the face recognition task, particularly the face verification here. Face verification is a crucial task in recent days and it has been deployed to plenty of applications, such as access control, surveillance, and automatic personal log-on for mobile devices. With the increasing amount of data, deep convolutional neural networks can achieve very high accuracy for the face verification task. Beyond exceptional performances, deep face verification models need more interpretability so that we can trust the results they generate. In this paper, we propose a novel similarity metric, called explainable cosine (xCos), that comes with a learnable module that can be plugged into most of the verification models to provide meaningful explanations. With the help of xCos, we can see which parts of the two input faces are similar, where the model pays its attention to, and how the local similarities are weighted to form the output xCos score. We demonstrate the effectiveness of our proposed method on LFW and various competitive benchmarks, resulting in not only providing novel and desiring model interpretability for face verification but also ensuring the accuracy as plugging into existing face recognition models.