Deep Learning Face Representation by Joint Identification-Verification
arXiv:1406.4773
Abstract
The key challenge of face recognition is to develop effective feature representations for reducing intra-personal variations while enlarging inter-personal differences. In this paper, we show that it can be well solved with deep learning and using both face identification and verification signals as supervision. The Deep IDentification-verification features (DeepID2) are learned with carefully designed deep convolutional networks. The face identification task increases the inter-personal variations by drawing DeepID2 extracted from different identities apart, while the face verification task reduces the intra-personal variations by pulling DeepID2 extracted from the same identity together, both of which are essential to face recognition. The learned DeepID2 features can be well generalized to new identities unseen in the training data. On the challenging LFW dataset, 99.15% face verification accuracy is achieved. Compared with the best deep learning result on LFW, the error rate has been significantly reduced by 67%.
References in corpus (2)
Cited by in corpus (65)
- Learning Deep Embeddings with Histogram Loss
- Deep Adaptive Feature Embedding with Local Sample Distributions for Person Re-identification
- Enabling and Emerging Technologies for Social Distancing: A Comprehensive Survey and Open Problems
- Personalized Age Progression with Bi-level Aging Dictionary Learning
- Deep learning and face recognition: the state of the art
- Robust Screening of COVID-19 from Chest X-ray via Discriminative Cost-Sensitive Learning
- Support Vector Guided Softmax Loss for Face Recognition
- A Multi-view CNN-based Acoustic Classification System for Automatic Animal Species Identification
- Striking the Right Balance with Uncertainty
- Graph-RISE: Graph-Regularized Image Semantic Embedding
- AdaCos: Adaptively Scaling Cosine Logits for Effectively Learning Deep Face Representations
- ShrinkTeaNet: Million-scale Lightweight Face Recognition via Shrinking Teacher-Student Networks
- A Light Dual-Task Neural Network for Haze Removal
- A survey of face recognition techniques under occlusion
- A Deep Four-Stream Siamese Convolutional Neural Network with Joint Verification and Identification Loss for Person Re-detection
- Cross-Resolution Face Recognition via Prior-Aided Face Hallucination and Residual Knowledge Distillation
- Max-margin Class Imbalanced Learning with Gaussian Affinity
- Towards Universal Representation Learning for Deep Face Recognition
- Decorrelated Adversarial Learning for Age-Invariant Face Recognition
- Video Face Recognition: Component-wise Feature Aggregation Network (C-FAN)
- GroupFace: Learning Latent Groups and Constructing Group-based Representations for Face Recognition
- Generative One-Shot Face Recognition
- Character-level Chinese Writer Identification using Path Signature Feature, DropStroke and Deep CNN
- Zooming into Face Forensics: A Pixel-level Analysis
- Attribute Adaptive Margin Softmax Loss using Privileged Information
- Hierarchical Feature Embedding for Attribute Recognition
- BroadFace: Looking at Tens of Thousands of People at Once for Face Recognition
- Multi-Prototype Networks for Unconstrained Set-based Face Recognition
- Signal-to-Noise Ratio: A Robust Distance Metric for Deep Metric Learning
- Anatomy-Aware Siamese Network: Exploiting Semantic Asymmetry for Accurate Pelvic Fracture Detection in X-ray Images
- Learning to Learn in a Semi-Supervised Fashion
- Dependency Aware Filter Pruning
- Learning to Cluster Faces via Confidence and Connectivity Estimation
- Triplet Distillation for Deep Face Recognition
- DropSample: A New Training Method to Enhance Deep Convolutional Neural Networks for Large-Scale Unconstrained Handwritten Chinese Character Recognition
- Style Transfer Applied to Face Liveness Detection with User-Centered Models
- Asymmetric Rejection Loss for Fairer Face Recognition
- Discriminability Distillation in Group Representation Learning
- Disentanglement for Discriminative Visual Recognition
- Learning Semantic Vector Representations of Source Code via a Siamese Neural Network
- Metric Classification Network in Actual Face Recognition Scene
- An Attention-Based Speaker Naming Method for Online Adaptation in Non-Fixed Scenarios
- A Multi-Resolution Word Embedding for Document Retrieval from Large Unstructured Knowledge Bases
- Learning Discriminative Features Via Weights-biased Softmax Loss
- MassFace: an efficient implementation using triplet loss for face recognition
- Deep Multi-task Multi-label CNN for Effective Facial Attribute Classification
- Semi-Siamese Training for Shallow Face Learning
- Directional Deep Embedding and Appearance Learning for Fast Video Object Segmentation
- Adma: A Flexible Loss Function for Neural Networks
- Alpha-Net: Architecture, Models, and Applications
- Learning discriminative features in sequence training without requiring framewise labelled data
- MSFD:Multi-Scale Receptive Field Face Detector
- On Learning Density Aware Embeddings
- Occlusion-guided compact template learning for ensemble deep network-based pose-invariant face recognition
- Face representation by deep learning: a linear encoding in a parameter space?
- A Novel Perspective to Zero-shot Learning: Towards an Alignment of Manifold Structures via Semantic Feature Expansion
- AMC-Loss: Angular Margin Contrastive Loss for Improved Explainability in Image Classification
- A Discriminative Learned CNN Embedding for Remote Sensing Image Scene Classification
- Representation Learning from Limited Educational Data with Crowdsourced Labels
- Adaptive Deep Metric Embeddings for Person Re-Identification under Occlusions
- Cosmetic-Aware Makeup Cleanser
- Identity Recognition in Intelligent Cars with Behavioral Data and LSTM-ResNet Classifier
- Unknown Identity Rejection Loss: Utilizing Unlabeled Data for Face Recognition
- Learn to Propagate Reliably on Noisy Affinity Graphs
- ECML: An Ensemble Cascade Metric Learning Mechanism towards Face Verification