An Incremental Unified Framework for Small Defect Inspection

1The Hong Kong University of Science and Technology (Guangzhou)
2The Hong Kong University of Science and Technology   3HKUST(GZ)-SmartMore Joint Lab
4Zhejiang University   5Zhejiang Lab 6SmartMore Corporation   7Hong Kong Industrial Artificial Intelligence & Robotics Centre   8Hong Kong Productivity Council  

We present the Incremental Unified Framework, which can reduce the feature conflict problem when continuously integrating new objects in the pipeline, making it advantageous in object incremental learning scenarios.

Video


BibTeX

@article{tang2023incremental,
  title={An Incremental Unified Framework for Small Defect Inspection},
  author={Tang, Jiaqi and Lu, Hao and Xu, Xiaogang and Wu, Ruizheng and Hu, Sixing and Zhang, Tong and Cheng, Tsz Wa and Ge, Ming and Chen, Ying-Cong and Tsung, Fugee},
  booktitle={ECCV},
  year={2024}
}

Acknowledgment

The research work was sponsored by AIR@InnoHK.