DeepAI AI Chat
Log In Sign Up

Learning to Cluster Faces via Transformer

by   Jinxing Ye, et al.

Face clustering is a useful tool for applications like automatic face annotation and retrieval. The main challenge is that it is difficult to cluster images from the same identity with different face poses, occlusions, and image quality. Traditional clustering methods usually ignore the relationship between individual images and their neighbors which may contain useful context information. In this paper, we repurpose the well-known Transformer and introduce a Face Transformer for supervised face clustering. In Face Transformer, we decompose the face clustering into two steps: relation encoding and linkage predicting. Specifically, given a face image, a relation encoder module aggregates local context information from its neighbors and a linkage predictor module judges whether a pair of images belong to the same cluster or not. In the local linkage graph view, Face Transformer can generate more robust node and edge representations compared to existing methods. Experiments on both MS-Celeb-1M and DeepFashion show that our method achieves state-of-the-art performance, e.g., 91.12% in pairwise F-score on MS-Celeb-1M.


Password-conditioned Anonymization and Deanonymization with Face Identity Transformers

Cameras are prevalent in our daily lives, and enable many useful systems...

FaceMap: Towards Unsupervised Face Clustering via Map Equation

Face clustering is an essential task in computer vision due to the explo...

Learn to Cluster Faces via Pairwise Classification

Face clustering plays an essential role in exploiting massive unlabeled ...

Linkage Based Face Clustering via Graph Convolution Network

In this paper, we present an accurate and scalable approach to the face ...

Ada-NETS: Face Clustering via Adaptive Neighbour Discovery in the Structure Space

Face clustering has attracted rising research interest recently to take ...

Protecting Celebrities with Identity Consistency Transformer

In this work we propose Identity Consistency Transformer, a novel face f...

Structure-Aware Face Clustering on a Large-Scale Graph with 10^7 Nodes

Face clustering is a promising method for annotating unlabeled face imag...