Rethinking Robust Representation Learning Under Fine-grained Noisy Faces

by   Bingqi Ma, et al.
SenseTime Corporation
Institute of Computing Technology, Chinese Academy of Sciences

Learning robust feature representation from large-scale noisy faces stands out as one of the key challenges in high-performance face recognition. Recent attempts have been made to cope with this challenge by alleviating the intra-class conflict and inter-class conflict. However, the unconstrained noise type in each conflict still makes it difficult for these algorithms to perform well. To better understand this, we reformulate the noise type of each class in a more fine-grained manner as N-identities|K^C-clusters. Different types of noisy faces can be generated by adjusting the values of . Based on this unified formulation, we found that the main barrier behind the noise-robust representation learning is the flexibility of the algorithm under different N, K, and C. For this potential problem, we propose a new method, named Evolving Sub-centers Learning (ESL), to find optimal hyperplanes to accurately describe the latent space of massive noisy faces. More specifically, we initialize M sub-centers for each class and ESL encourages it to be automatically aligned to N-identities|K^C-clusters faces via producing, merging, and dropping operations. Images belonging to the same identity in noisy faces can effectively converge to the same sub-center and samples with different identities will be pushed away. We inspect its effectiveness with an elaborate ablation study on the synthetic noisy dataset with different N, K, and C. Without any bells and whistles, ESL can achieve significant performance gains over state-of-the-art methods on large-scale noisy faces


page 1

page 2

page 3

page 4


Unknown Identity Rejection Loss: Utilizing Unlabeled Data for Face Recognition

Face recognition has advanced considerably with the availability of larg...

Killing Two Birds with One Stone:Efficient and Robust Training of Face Recognition CNNs by Partial FC

Learning discriminative deep feature embeddings by using million-scale i...

RetouchingFFHQ: A Large-scale Dataset for Fine-grained Face Retouching Detection

The widespread use of face retouching filters on short-video platforms h...

Face Morphing: Fooling a Face Recognition System Is Simple!

State-of-the-art face recognition (FR) approaches have shown remarkable ...

Deep Representation Learning Characterized by Inter-class Separation for Image Clustering

Despite significant advances in clustering methods in recent years, the ...

The Fixed Sub-Center: A Better Way to Capture Data Complexity

Treating class with a single center may hardly capture data distribution...

Face Verification with Challenging Imposters and Diversified Demographics

Face verification aims to distinguish between genuine and imposter pairs...

Please sign up or login with your details

Forgot password? Click here to reset