Enhancing Noise Resilience in Face Clustering via Sparse Differential Transformer
By: Dafeng Zhang, Yongqi Song, Shizhuo Liu
Potential Business Impact:
Finds faces in pictures better.
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.
Similar Papers
Speedrunning ImageNet Diffusion
CV and Pattern Recognition
Makes AI create better pictures faster.
Explainable Transformer-CNN Fusion for Noise-Robust Speech Emotion Recognition
Sound
Helps computers understand emotions even with background noise.
Hyperspectral data augmentation with transformer-based diffusion models
CV and Pattern Recognition
Makes satellite pictures identify more forest types.