Consensus-Driven Propagation in Massive Unlabeled Data for Face Recognition

  title={Consensus-Driven Propagation in Massive Unlabeled Data for Face Recognition},
  author={Xiaohang Zhan and Ziwei Liu and Junjie Yan and Dahua Lin and Chen Change Loy},
Face recognition has witnessed great progress in recent years, mainly attributed to the high-capacity model designed and the abundant labeled data collected. However, it becomes more and more prohibitive to scale up the current million-level identity annotations. In this work, we show that unlabeled face data can be as effective as the labeled ones. Here, we consider a setting closely mimicking the real-world scenario, where the unlabeled data are collected from unconstrained environments and… 

Improving Face Recognition by Clustering Unlabeled Faces in the Wild

A novel identity separation method based on extreme value theory is formulated as an out-of-distribution detection algorithm, and greatly reduces the problems caused by overlapping-identity label noise in large-scale face recognition.

Neighborhood-Aware Attention Network for Semi-supervised Face Recognition

  • Qi ZhangZhen LeiS. Li
  • Computer Science
    2020 International Joint Conference on Neural Networks (IJCNN)
  • 2020
A bottom- up method, Neighborhood-Aware Attention Network (NAAN), for semi-supervised face recognition that clusters unlabeled face images by collaboratively predicting pairwise relations based on their neighborhood information.

Learn to Cluster Faces via Pairwise Classification

This paper forms the face clustering task as a pairwise relationship classification task, avoiding the memory-consuming learning on large-scale graphs and proposes a rank-weighted density to guide the selection of pairs sent to the classifier.

Learning to Cluster Faces on an Affinity Graph

This work explores a novel approach, namely, learning to cluster instead of relying on hand-crafted criteria, and proposes a framework based on graph convolutional network, which combines a detection and a segmentation module to pinpoint face clusters.

Unknown Identity Rejection Loss: Utilizing Unlabeled Data for Face Recognition

This paper proposes the novel Unknown Identity Rejection (UIR) loss to utilize the unlabeled data, which categorizes identities in unconstrained environment into the known set and the unknown set and forces the model to reject unknown identities provided by the unl Isabeled dataset via this loss.

VirFace: Enhancing Face Recognition via Unlabeled Shallow Data

This paper proposes a novel face recognition method, named VirFace, to effectively exploit the unlabeled shallow data for face recognition, which enlarges the inter-class distance by injecting the unlabed data as new identities, while VirInstance produces virtual instances sampled from the learned distribution of each identity to further enlarge theInter- class distance.

Learning to Cluster Faces via Confidence and Connectivity Estimation

This paper proposes a fully learnable clustering framework without requiring a large number of overlapped subgraphs, and transforms the clustering problem into two sub-problems, designed to estimate the confidence of vertices and the connectivity of edges, respectively.

Asymmetric Rejection Loss for Fairer Face Recognition

An Asymmetric Rejection Loss, which aims at making full use of unlabeled images of under-represented groups, to reduce the racial bias of face recognition models and outperforming state-of-the-art semi-supervision methods.

Caption-Supervised Face Recognition: Training a State-of-the-Art Face Model without Manual Annotation

A simple yet effective method, which trains a state-of-the-art face recognition model by progressively expanding the labeled set via both selective propagation and caption-driven expansion, and shows the great potential of caption-supervised face recognition.

On Mitigating Hard Clusters for Face Clustering

Two novel modules are introduced, Neighborhood-Diffusion-based Density (NDDe) and Transition-Probability-based Distance (TPDi), based on which the standard Density Peak Clustering algorithm can be applied with a uniform threshold, to tackle the problem of identifying small or sparse face image clusters.



Deep Imbalanced Learning for Face Recognition and Attribute Prediction

Cluster-based Large Margin Local Embedding (CLMLE), when combined with a simple k-nearest cluster algorithm, shows significant improvements in accuracy over existing methods on both face recognition and face attribute prediction tasks that exhibit imbalanced class distribution.

A data-driven approach to cleaning large face datasets

An approach to building face datasets that starts with detecting faces in images returned from searches for public figures on the Internet, followed by discarding those not belonging to each queried person, and is releasing the FaceScrub dataset.

FaceNet: A unified embedding for face recognition and clustering

A system that directly learns a mapping from face images to a compact Euclidean space where distances directly correspond to a measure offace similarity, and achieves state-of-the-art face recognition performance using only 128-bytes perface.

MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition

A benchmark task to recognize one million celebrities from their face images, by using all the possibly collected face images of this individual on the web as training data, which could lead to one of the largest classification problems in computer vision.

Deep Learning Face Attributes in the Wild

A novel deep learning framework for attribute prediction in the wild that cascades two CNNs, LNet and ANet, which are fine-tuned jointly with attribute tags, but pre-trained differently.

Semi-Supervised Sparse Representation Based Classification for Face Recognition With Insufficient Labeled Samples

This paper addresses the problem of face recognition when there is only few, or even only a single, labeled examples of the face that the authors wish to recognize, and proposes a method called semi-supervised sparse representation-based classification, based on recent work on sparsity.

Mix-and-Match Tuning for Self-Supervised Semantic Segmentation

With the proposed M&M approach, for the first time, a self-supervision method can achieve comparable or even better performance compared to its ImageNet pretrained counterpart on both PASCAL VOC2012 dataset and CityScapes dataset.

The Devil of Face Recognition is in the Noise

This work contributes cleaned subsets of popular face databases, i.e., MegaFace and MS-Celeb-1M datasets, and builds a new large-scale noise-controlled IMDb-Face dataset, and investigates ways to improve data cleanliness, including a comprehensive user study on the influence of data labeling strategies to annotation accuracy.

Pose-Robust Face Recognition via Deep Residual Equivariant Mapping

A novel Deep Residual EquivAriant Mapping (DREAM) block is formulated, which is capable of adaptively adding residuals to the input deep representation to transform a profile face representation to a canonical pose that simplifies recognition.

Semi-supervised learning with graphs

A series of novel semi-supervised learning approaches arising from a graph representation, where labeled and unlabeled instances are represented as vertices, and edges encode the similarity between instances are presented.