2021 IEEE International Conference on Image Processing

19-22 September 2021 • Anchorage, Alaska, USA

Imaging Without Borders

2021 IEEE International Conference on Image Processing

19-22 September 2021 • Anchorage, Alaska, USA

Login Paper Search My Schedule Paper Index Help

My ICIP 2021 Schedule

Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.
  1. Create a login based on your email (takes less than one minute)
  2. Perform 'Paper Search'
  3. Select papers that you desire to save in your personalized schedule
  4. Click on 'My Schedule' to see the current list of selected papers
  5. Click on 'Printable Version' to create a separate window suitable for printing (the header and menu will appear, but will not actually print)

Paper Detail

Paper IDMLR-APPL-IVASR-4.1
Paper Title DEFECT INSPECTION USING GRAVITATION LOSS AND SOFT LABELS
Authors Zhihao Guan, Zidong Guo, Jie Lyu, Zejian Yuan, Xi'an Jiaotong University, China
SessionMLR-APPL-IVASR-4: Machine learning for image and video analysis, synthesis, and retrieval 4
LocationArea B
Session Time:Tuesday, 21 September, 13:30 - 15:00
Presentation Time:Tuesday, 21 September, 13:30 - 15:00
Presentation Poster
Topic Applications of Machine Learning: Machine learning for image & video analysis, synthesis, and retrieval
IEEE Xplore Open Preview  Click here to view in IEEE Xplore
Abstract Defect inspection is a widely studied computer vision task with a vast range of applications. However, due to the great variety of defects and high difficulty of collecting ample abnormal images of rare occasions, such a task full of confusing noisy samples faces tremendous challenges of generalization. In this paper, we propose a practical framework for defect inspection to better discover and utilize the connections among these samples. Specifically, Gravitation Loss is proposed to enhance the discriminative power of embedding vectors learned by neural networks. Besides, Soft Loss is designed by introducing soft labels which provide more supervision for noisy samples to improve generalization. With joint supervision of Gravitation Loss, Soft Loss, and a regular classification loss, experimental results show that our method outperforms other state-of-the-art approaches on a newly-built resin plug-hole dataset.