Activation Template Matching Loss for Explainable Face Recognition
Not on the map. Why?
Abstract (arXiv)
Can we construct an explainable face recognition network able to learn a facial part-based feature like eyes, nose, mouth and so forth, without any manual annotation or additionalsion datasets? In this paper, we propose a generic Explainable Channel Loss (ECLoss) to construct an explainable face recognition network. The explainable network trained with ECLoss can easily learn the facial part-based representation on the target convolutional layer, where an individual channel can detect a certain face part. Our experiments on dozens of datasets show that ECLoss achieves superior explainability metrics, and at the same time improves the performance of face verification without face alignment. In addition, our visualization results also illustrate the effectiveness of the proposed ECLoss.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 34 of its 78 references that are in the map. First posted on arXiv 5 Jul 2022.
Builds on
34 of 78 references.
References · 34
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
- 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
- 2016Feature Pyramid Networks for Object Detectioncited by 5,021
- 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,833
- 2015Learning Deep Features for Discriminative Localizationcited by 2,430
- 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
- 2013Visualizing and Understanding Convolutional Networkscited by 2,278
- 2018CosFace: Large Margin Cosine Loss for Deep Face Recognitioncited by 968
- 2017Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networkscited by 936
- 2017SphereFace: Deep Hypersphere Embedding for Face Recognitioncited by 733
- 2017Network Dissection: Quantifying Interpretability of Deep Visual Representationscited by 703
22 more
- 2016MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognitioncited by 621
- 2017Interpretable Explanations of Black Boxes by Meaningful Perturbationcited by 611
- 2019Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networkscited by 575
- 2014Understanding Deep Image Representations by Inverting Themcited by 399
- 2017Cross-Age LFW: A Database for Studying Cross-Age Face Recognition in Unconstrained Environmentscited by 258
- 2020Understanding the Role of Individual Units in a Deep Neural Networkcited by 254
- 2017NormFace: L2 Hypersphere Embedding for Face Verificationcited by 237
- 2018Techniques for Interpretable Machine Learningcited by 237
- 2020Eigen-CAM: Class Activation Map using Principal Componentscited by 188
- 2015Inverting Visual Representations with Convolutional Networkscited by 168
- 2020Partial FC: Training 10 Million Identities on a Single Machinecited by 163
- 2017Interpretable Convolutional Neural Networkscited by 161
- 2018Visual Interpretability for Deep Learning: a Surveycited by 155
- 2017Interpreting Deep Visual Representations via Network Dissectioncited by 103
- 2018Ring loss: Convex Feature Normalization for Face Recognitioncited by 39
- 2020GroupFace: Learning Latent Groups and Constructing Group-based Representations for Face Recognitioncited by 38
- 2018Towards Interpretable Face Recognitioncited by 30
- 2020xCos: An Explainable Cosine Metric for Face Verification Taskcited by 24
- 2019Interpretable CNNs for Object Classificationcited by 16
- 2016Template Adaptation for Face Verification and Identificationcited by 13
- 2021Group-wise Inhibition based Feature Regularization for Robust Classificationcited by 11
- 2022Robust Representation via Dynamic Feature Aggregationcited by 2
Built on by
Citing papers per year: 2025: 2.
2 papers.