Learning Face Representation from Scratch
read the original 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.
This paper has not been read by Pith yet.
Forward citations
Cited by 15 Pith papers
-
Non-Colliding Biometric Identities for Digital Entities: Geometry, Capacity, and Million-Scale Virtual Identity Provisioning
Introduces BIP framework and GapGen generator to allocate and synthesize millions of non-colliding virtual face identities within gaps of the real face manifold.
-
PreFIQs: Face Image Quality Is What Survives Pruning
Face image quality is quantified as the Euclidean distance between embeddings from a pre-trained face recognition model and its pruned version, achieving competitive or superior results without training or supervision.
-
StyleID: A Perception-Aware Dataset and Metric for Stylization-Agnostic Facial Identity Recognition
StyleID supplies human-perception-aligned benchmarks and fine-tuned encoders that improve facial identity recognition robustness across stylization types and strengths.
-
BID-LoRA: A Parameter-Efficient Framework for Continual Learning and Unlearning
BID-LoRA uses bi-directional low-rank adapters with retain/new/unlearn pathways and escape unlearning to enable continual learning and unlearning while minimizing knowledge leakage and parameter updates.
-
Multiple-Identity Image Attacks Against Face-based Identity Verification
The paper shows that multiple-identity image attacks succeed due to modest angular separation between matching (~90°) and non-matching (40-60°) face representations, with image morphing and representation inversion re...
-
On the Impact of Face Segmentation-Based Background Removal on Recognition and Morphing Attack Detection
Face segmentation for background removal systematically impacts both face recognition performance and morphing attack detection in unconstrained scenarios.
-
Reinforcement-Guided Synthetic Data Generation for Privacy-Sensitive Identity Recognition
A reinforcement learning approach adapts general generative models to produce synthetic data that boosts identity recognition accuracy and generalization under privacy constraints.
-
Are Face Embeddings Compatible Across Deep Neural Network Models?
Simple affine transformations align face embeddings across different DNN models, substantially improving cross-model identification and verification performance.
-
Does Head Pose Correction Improve Biometric Facial Recognition?
Naive use of head-pose correction and restoration tools degrades biometric facial recognition accuracy, while selective use of CFR-GAN plus CodeFormer produces measurable gains.
-
Knowledge Amalgamation from Heterogeneous Networks by Common Feature Learning
Common feature learning transforms features from heterogeneous teacher networks into a shared space so a student model can imitate them all and outperform individual teachers without annotations.
-
Lightweight Cross-Spectral Face Recognition via Contrastive Alignment and Distillation
A lightweight hybrid CNN-Transformer framework for heterogeneous face recognition achieves competitive performance on cross-spectral benchmarks and standard RGB tasks using contrastive alignment and distillation.
-
Exploring Factors for Improving Low Resolution Face Recognition
Deep face models trained on MS-Celeb-1M and fine-tuned on VGGFace2 achieve state-of-the-art accuracies on SCFace and ICB-RW low-resolution benchmarks without using any of their training data by leveraging appearance v...
-
Primate Face Identification in the Wild
A pairwise-augmented loss on CNNs is reported to deliver state-of-the-art accuracy on primate face classification, verification, closed-set and open-set identification for two species.
-
SoK: A Comprehensive Analysis of the Current Status of Neural Tangent Generalization Attacks with Research Directions
NTGA is the first clean-label generalization attack under black-box settings but is vulnerable to adversarial training and image transformations, with newer attacks outperforming it.
-
Slim-CNN: A Light-Weight CNN for Face Attribute Prediction
Slim-Net uses stacked Slim Modules of depthwise separable convolutions to predict face attributes on CelebA at 91.24% accuracy with at least 25 times fewer parameters than comparable models.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.