mlsanityData to 7 Oct 2026

Improved Face Representation via Joint Label Classification and Supervised Contrastive Clustering

arXiv 2312.04029 ↗First posted 7 Dec 2023cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Face clustering tasks can learn hierarchical semantic information from large-scale data, which has the potential to help facilitate face recognition. However, there are few works on this problem. This paper explores it by proposing a joint optimization task of label classification and supervised contrastive clustering to introduce the cluster knowledge to the traditional face recognition task in two ways. We first extend ArcFace with a cluster-guided angular margin to adjust the within-class feature distribution according to the hard level of face clustering. Secondly, we propose a supervised contrastive clustering approach to pull the features to the cluster center and propose the cluster-aligning procedure to align the cluster center and the learnable class center in the classifier for joint training. Finally, extensive qualitative and quantitative experiments on popular facial benchmarks demonstrate the effectiveness of our paradigm and its superiority over the existing approaches to face recognition.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 28 of its 43 references that are in the map. First posted on arXiv 7 Dec 2023.

Builds on

28 of 43 references.

References · 28

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  3. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  4. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,833
  5. 2018CosFace: Large Margin Cosine Loss for Deep Face Recognitioncited by 968
  6. 2017SphereFace: Deep Hypersphere Embedding for Face Recognitioncited by 733
  7. 2020Prototypical Contrastive Learning of Unsupervised Representationscited by 636
  8. 2016MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognitioncited by 621
  9. 2020Circle Loss: A Unified Perspective of Pair Similarity Optimizationcited by 402
  10. 2020CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognitioncited by 320
  11. 2018Additive Margin Softmax for Face Verificationcited by 275
  12. 2020Contrastive Clusteringcited by 264
16 more
  1. 2017Cross-Age LFW: A Database for Studying Cross-Age Face Recognition in Unconstrained Environmentscited by 258
  2. 2015The MegaFace Benchmark: 1 Million Faces for Recognition at Scalecited by 199
  3. 2021ElasticFace: Elastic Margin Loss for Deep Face Recognitioncited by 143
  4. 2019AdaCos: Adaptively Scaling Cosine Logits for Effectively Learning Deep Face Representationscited by 83
  5. 2020Towards Universal Representation Learning for Deep Face Recognitioncited by 78
  6. 2019Mis-classified Vector Guided Softmax Loss for Face Recognitioncited by 60
  7. 2019Linkage Based Face Clustering via Graph Convolution Networkcited by 55
  8. 2019Learning to Cluster Faces on an Affinity Graphcited by 50
  9. 2017Level Playing Field for Million Scale Face Recognitioncited by 43
  10. 2020Learning to Cluster Faces via Confidence and Connectivity Estimationcited by 42
  11. 2020GroupFace: Learning Latent Groups and Constructing Group-based Representations for Face Recognitioncited by 38
  12. 2020Domain Balancing: Face Recognition on Long-Tailed Domainscited by 32
  13. 2020BroadFace: Looking at Tens of Thousands of People at Once for Face Recognitioncited by 30
  14. 2021Structure-Aware Face Clustering on a Large-Scale Graph with bf107 Nodescited by 21
  15. 2020Semi-Siamese Training for Shallow Face Learningcited by 19
  16. 2019Attentional Feature-Pair Relation Networks for Accurate Face Recognitioncited by 9

Built on by

Not cited yet.