Boosting Multi-Label Image Classification with Complementary Parallel Self-Distillation

Multi-Label Image Classification (MLIC) appro-aches usually exploit label correlations to achieve good performance. However, emphasizing correlation like co-occurrence may overlook discriminative features and lead to model overfitting. In this study, we propose a generic framework named Parallel Self-Distillation (PSD) for boosting MLIC models. PSD decomposes the original MLIC task into several simpler MLIC sub-tasks via two elaborated complementary task decomposition strategies named Co-occurrence Graph Partition (CGP) and Dis-occurrence Graph Partition (DGP). Then, the MLIC models of fewer categories are trained with these sub-tasks in parallel for respectively learning the joint patterns and the category-specific patterns of labels. Finally, knowledge distillation is leveraged to learn a compact global ensemble of full categories with these learned patterns for reconciling the label correlation exploitation and model overfitting. Extensive results on MS-COCO and NUS-WIDE datasets demonstrate that our framework can be easily plugged into many MLIC approaches and improve performances of recent state-of-the-art approaches. The source code is released at https: //github. com/Robbie-Xu/CPSD.

Authors

• Jiazhi Xu
• Sheng Huang Sun Yat-sen University
• Fengtao Zhou
• Luwen Huangfu Fowler College of Business, San Diego State University
• Daniel Zeng
• Bo Liu Peking University

Keywords

• Computer Vision: Machine Learning for Vision
• Computer Vision: Recognition (object detection, categorization)
• Machine Learning: Multi-label