Abstract
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., statistically significant subgraphs, 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 crossdomain distribution with structural awareness. Extensive experiments demonstrate that the proposed SOMA achieves state-of-the-art performance. Codes are available at https://github.com/CityU-AIM-Group/SOMA.
Original language | English |
---|---|
Title of host publication | Proceedings - 2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023 |
Publisher | IEEE |
Pages | 15734-15744 |
Number of pages | 11 |
ISBN (Electronic) | 9798350307184 |
ISBN (Print) | 9798350307191 |
DOIs | |
Publication status | Published - Oct 2023 |
Event | 2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023 - Paris, France Duration: 2 Oct 2023 → 6 Oct 2023 https://iccv2023.thecvf.com/ (Conference website) https://ieeexplore.ieee.org/xpl/conhome/10376473/proceeding (Conference proceedings) |
Publication series
Name | Proceedings of the IEEE International Conference on Computer Vision |
---|---|
Publisher | IEEE |
ISSN (Print) | 1550-5499 |
ISSN (Electronic) | 2380-7504 |
Conference
Conference | 2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023 |
---|---|
Country/Territory | France |
City | Paris |
Period | 2/10/23 → 6/10/23 |
Internet address |
|
Scopus Subject Areas
- Software
- Computer Vision and Pattern Recognition