Diffuse and Refine : Intrinsic Knowledge Generation and Aggregation for Incremental Object Detection

Wang, Jianzhou and Wu, Yirui and Yuan, Lixin and Zhang, Wenxiao and Liu, Jun and Chen, Junyang and Wang, Huan and Wang, Wenhai (2025) Diffuse and Refine : Intrinsic Knowledge Generation and Aggregation for Incremental Object Detection. In: Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence :. Proceedings of the Thirty-ThirdInternational Joint Conference on Artificial Intelligence . IJCAI, pp. 6289-6297. ISBN 9781956792065

Abstract

Incremental Object Detection(IOD) targets at progressively extending capability of object detectors to recognize new classes. However, representation confusion between old and new classes leads to catastrophic forgetting. To alleviate this problem, we propose DiffKA, with intrinsic knowledge generated and aggregated by forward and backward diffusion, gradually establishing rigid class boundary. With incremental streaming data, forward diffusion spreads information to generate potential inter-class associations among new- and old-class prototypes within a hierarchical tree, named as Intrinsic Correlation Tree(ICTree), to store intrinsic knowledge. Afterwards, backward diffusion refines and aggregates the generated knowledge in ICTree, explicitly establishing rigid class boundary to mitigate representation confusion. To keep semantic consistency with extreme IOD settings, we reorganize semantic relevance of old- and new-class prototypes in paradigms to adaptively and effectively update DiffKA. Experiments on MS COCO dataset show DiffKA achieves state-of-the-art performance on IOD tasks with significant advantages.