# Enhancing Noise Resilience in Face Clustering via Sparse Differential Transformer

arXiv: https://arxiv.org/abs/2512.22612 · HTML: https://mlsanity.com/paper/2512.22612/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 31 references that are in the map.
- First posted on arXiv 27 Dec 2025.

## Builds on (most cited first, 18 of 18)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition](https://mlsanity.com/paper/1607.08221/) (2016)
- [Person Transfer GAN to Bridge Domain Gap for Person Re-Identification](https://mlsanity.com/paper/1711.08565/) (2017)
- [Re-ranking Person Re-identification with k-reciprocal Encoding](https://mlsanity.com/paper/1701.08398/) (2017)
- [WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition](https://mlsanity.com/paper/2103.04098/) (2021)
- [Linkage Based Face Clustering via Graph Convolution Network](https://mlsanity.com/paper/1903.11306/) (2019)
- [Learning to Cluster Faces on an Affinity Graph](https://mlsanity.com/paper/1904.02749/) (2019)
- [Learning to Cluster Faces via Confidence and Connectivity Estimation](https://mlsanity.com/paper/2004.00445/) (2020)
- [Structure-Aware Face Clustering on a Large-Scale Graph with bf107 Nodes](https://mlsanity.com/paper/2103.13225/) (2021)
- [Ada-NETS: Face Clustering via Adaptive Neighbour Discovery in the Structure Space](https://mlsanity.com/paper/2202.03800/) (2022)
- [Face Clustering: Representation and Pairwise Constraints](https://mlsanity.com/paper/1706.05067/) (2017)
- [Learn to Cluster Faces via Pairwise Classification](https://mlsanity.com/paper/2205.13117/) (2022)
- [On Mitigating Hard Clusters for Face Clustering](https://mlsanity.com/paper/2207.11895/) (2022)
- [Learning to Cluster Faces via Transformer](https://mlsanity.com/paper/2104.11502/) (2021)
- [FaceMap: Towards Unsupervised Face Clustering via Map Equation](https://mlsanity.com/paper/2203.10090/) (2022)
- [Robust Graph Structure Learning via Multiple Statistical Tests](https://mlsanity.com/paper/2210.03956/) (2022)
- [Face Clustering via Early Stopping and Edge Recall](https://mlsanity.com/paper/2408.13431/) (2024)

## Abstract (arXiv)

The method used to measure relationships between face embeddings plays a crucial role in determining the performance of face clustering. Existing methods employ the Jaccard similarity coefficient instead of the cosine distance to enhance the measurement accuracy. However, these methods introduce too many irrelevant nodes, producing Jaccard coefficients with limited discriminative power and adversely affecting clustering performance. To address this issue, we propose a prediction-driven Top-K Jaccard similarity coefficient that enhances the purity of neighboring nodes, thereby improving the reliability of similarity measurements. Nevertheless, accurately predicting the optimal number of neighbors (Top-K) remains challenging, leading to suboptimal clustering results. To overcome this limitation, we develop a Transformer-based prediction model that examines the relationships between the central node and its neighboring nodes near the Top-K to further enhance the reliability of similarity estimation. However, vanilla Transformer, when applied to predict relationships between nodes, often introduces noise due to their overemphasis on irrelevant feature relationships. To address these challenges, we propose a Sparse Differential Transformer (SDT), instead of the vanilla Transformer, to eliminate noise and enhance the model's anti-noise capabilities. Extensive experiments on multiple datasets, such as MS-Celeb-1M, demonstrate that our approach achieves state-of-the-art (SOTA) performance, outperforming existing methods and providing a more robust solution for face clustering.