Novel Scenes & Classes: Towards Adaptive Open-set Object Detection

Wuyang Li, Xiaoqing Guo, Yixuan Yuan; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2023, pp. 15780-15790


Domain Adaptive Object Detection (DAOD) transfers an object detector to a novel domain free of labels. However, in the real world, besides encountering novel scenes, novel domains always contain novel-class objects de facto, which are ignored in existing research. Thus, we formulate and study a more practical setting, Adaptive Open-set Object Detection (AOOD), considering both novel scenes and classes. Directly combing off-the-shelled cross-domain and open-set approaches is sub-optimal since their low-order dependence, e.g., the confidence score, is insufficient for the AOOD with two dimensions of novel information. To address this, we propose a novel Structured mOtif MAtching (SOMA) framework for AOOD, which models the high-order relation with motifs, i.e., a statistically significant subgraph, and formulates AOOD solution as motif matching to learn with high-order patterns. In a nutshell, SOMA consists of Structure-aware Novel-class Learning (SNL) and Structure-aware Transfer Learning (STL). As for SNL, we establish an instance-oriented graph to capture the class-independent object feature hidden in different base classes. Then, a high-order metric is proposed to match the most significant motif as high-order patterns, serving for motif-guided novel-class learning. In STL, we set up a semantic-oriented graph to model the class-dependent relation across domains, and match unlabelled objects with high-order motifs to align the cross-domain distribution with structural awareness. Extensive experiments demonstrate that the proposed SOMA achieves state-of-the-art performance. Codes will be released publicly for further study.

Related Material

[pdf] [supp]
@InProceedings{Li_2023_ICCV, author = {Li, Wuyang and Guo, Xiaoqing and Yuan, Yixuan}, title = {Novel Scenes \& Classes: Towards Adaptive Open-set Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15780-15790} }