Spectral Feature Transformation for Person Re-identification
This work addresses person re-identification for surveillance and security applications, offering an incremental improvement by integrating spectral clustering into existing CNNs.
The paper tackles the problem of person re-identification by proposing a spectral feature transformation that incorporates sample relations into CNN-based feature learning, resulting in outperforming previous state-of-the-art methods on four public benchmarks by a considerable margin.
With the surge of deep learning techniques, the field of person re-identification has witnessed rapid progress in recent years. Deep learning based methods focus on learning a feature space where samples are clustered compactly according to their corresponding identities. Most existing methods rely on powerful CNNs to transform the samples individually. In contrast, we propose to consider the sample relations in the transformation. To achieve this goal, we incorporate spectral clustering technique into CNN. We derive a novel module named Spectral Feature Transformation and seamlessly integrate it into existing CNN pipeline with negligible cost,which makes our method enjoy the best of two worlds. Empirical studies show that the proposed approach outperforms previous state-of-the-art methods on four public benchmarks by a considerable margin without bells and whistles.