Learning Face Representation from Scratch
arXiv:1411.7923
Abstract
Pushing by big data and deep convolutional neural network (CNN), the performance of face recognition is becoming comparable to human. Using private large scale training datasets, several groups achieve very high performance on LFW, i.e., 97% to 99%. While there are many open source implementations of CNN, none of large scale face dataset is publicly available. The current situation in the field of face recognition is that data is more important than algorithm. To solve this problem, this paper proposes a semi-automatical way to collect face images from Internet and builds a large scale dataset containing about 10,000 subjects and 500,000 images, called CASIAWebFace. Based on the database, we use a 11-layer CNN to learn discriminative representation and obtain state-of-theart accuracy on LFW and YTF. The publication of CASIAWebFace will attract more research groups entering this field and accelerate the development of face recognition in the wild.
References in corpus (3)
Cited by in corpus (37)
- DeepID3: Face Recognition with Very Deep Neural Networks
- Cross-Age LFW: A Database for Studying Cross-Age Face Recognition in Unconstrained Environments
- MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition
- Sampling Matters in Deep Embedding Learning
- von Mises-Fisher Mixture Model-based Deep learning: Application to Face Verification
- Range Loss for Deep Face Recognition with Long-tail
- When Face Recognition Meets with Deep Learning: an Evaluation of Convolutional Neural Networks for Face Recognition
- FaceNet2ExpNet: Regularizing a Deep Face Recognition Net for Expression Recognition
- DeepGestalt - Identifying Rare Genetic Syndromes Using Deep Learning
- Deep Joint Face Hallucination and Recognition
- Inference-Based Similarity Search in Randomized Montgomery Domains for Privacy-Preserving Biometric Identification
- Noisy Softmax: Improving the Generalization Ability of DCNN via Postponing the Early Softmax Saturation
- Feeding Hand-Crafted Features for Enhancing the Performance of Convolutional Neural Networks
- Peak-Piloted Deep Network for Facial Expression Recognition
- Not Afraid of the Dark: NIR-VIS Face Recognition via Cross-spectral Hallucination and Low-rank Embedding
- Temporal Non-Volume Preserving Approach to Facial Age-Progression and Age-Invariant Face Recognition
- Model Distillation with Knowledge Transfer from Face Classification to Alignment and Verification
- Contrastive-center loss for deep neural networks
- Web-Scale Training for Face Identification
- Cardea: Context-Aware Visual Privacy Protection from Pervasive Cameras
- Recent Progress of Face Image Synthesis
- Improving Heterogeneous Face Recognition with Conditional Adversarial Networks
- Regressing Robust and Discriminative 3D Morphable Models with a very Deep Neural Network
- Learning a Repression Network for Precise Vehicle Search
- Learning Robust Deep Face Representation
- Pose-Aware Person Recognition
- Robust LSTM-Autoencoders for Face De-Occlusion in the Wild
- UV-GAN: Adversarial Facial UV Map Completion for Pose-invariant Face Recognition
- VIPLFaceNet: An Open Source Deep Face Recognition SDK
- Probabilistic Neural Network with Complex Exponential Activation Functions in Image Recognition using Deep Learning Framework
- Quality Classified Image Analysis with Application to Face Detection and Recognition
- When 3D-Aided 2D Face Recognition Meets Deep Learning: An extended UR2D for Pose-Invariant Face Recognition
- Automatically Building Face Datasets of New Domains from Weakly Labeled Data with Pretrained Models
- ICFVR 2017: 3rd International Competition on Finger Vein Recognition
- Sentiment Recognition in Egocentric Photostreams
- Entropy Non-increasing Games for the Improvement of Dataflow Programming
- Fast Landmark Localization with 3D Component Reconstruction and CNN for Cross-Pose Recognition