Unsupervised person re-identification (re-ID) attracts growing attention due to its broad prospects in practical applications. State-of-the-art unsupervised re-ID approaches combine clustering-based pseudo-label prediction with feature fine-tuning. However, pseudo labels generated directly by clustering are not always reliable and inevitably contain noisy labels. To tackle these challenges, we propose a novel noise inhibition framework to estimate the confidence of each pseudo label and actively correct noisy labels. By introducing the silhouette coefficient, our method can estimate the pseudo-label confidence without any extra model or data, and calculate the correction matrix to correct clustering results directly. However, the silhouette coefficient is usually applied on the hyper-parameters selection of clustering algorithms. In order to make the silhouette coefficient more suitable for estimation and correction tasks, we calibrate the Jaccard distance matrix to alleviate the negative influence of the cluster size on the silhouette coefficient. Our proposed method brings significant improvement and achieves the state-of-the-art performance on benchmark datasets.
|Title of host publication||2022 IEEE International Conference on Multimedia and Expo (ICME)|
|Publisher||IEEE Computer Society|
|Publication status||Published (in print/issue) - 26 Aug 2022|
|Event||2022 IEEE International Conference on Multimedia and Expo, ICME 2022 - Taipei, Taiwan, Republic of China|
Duration: 18 Jul 2022 → 22 Jul 2022
|Name||Proceedings - IEEE International Conference on Multimedia and Expo|
|Conference||2022 IEEE International Conference on Multimedia and Expo, ICME 2022|
|Country/Territory||Taiwan, Republic of China|
|Period||18/07/22 → 22/07/22|
Bibliographical noteFunding Information:
*Shuying Zhao is the corresponding author. This work was supported by the Major Science and Technology Projects of Liaoning Province(No.2021JH1/10400049), the Fundation of Key Laboratory of Aerospace System Simulation(No.6142002200301), Fundation of Key Laboratory of Equipment Reliability(No.WD2C20205500306) and Fundamental Research Funds for the Central Universities (N2004022).
© 2022 IEEE.
- silhouette coefficient
- unsupervised person re-ID