2021 IEEE International Conference on Image Processing
19-22 September 2021 • Anchorage, Alaska, USA
Imaging Without Borders
| Paper ID | MLR-APPL-IVSMR-2.9 | ||
| Paper Title | OPEN-SET RECOGNITION WITH GRADIENT-BASED REPRESENTATIONS | ||
| Authors | Jinsol Lee, Ghassan AlRegib, Georgia Institute of Technology, United States | ||
| Session | MLR-APPL-IVSMR-2: Machine learning for image and video sensing, modeling and representation 2 | ||
| Location | Area D | ||
| Session Time: | Tuesday, 21 September, 15:30 - 17:00 | ||
| Presentation Time: | Tuesday, 21 September, 15:30 - 17:00 | ||
| Presentation | Poster | ||
| Topic | Applications of Machine Learning: Machine learning for image & video sensing, modeling, and representation | ||
| IEEE Xplore Open Preview | Click here to view in IEEE Xplore | ||
| Abstract | Neural networks for image classification tasks assume that any given image during inference belongs to one of the training classes. This closed-set assumption is challenged in real-world applications where models may encounter inputs of unknown classes. Open-set recognition aims to solve this problem by rejecting unknown classes while classifying known classes correctly. In this paper, we propose to utilize gradient-based representations obtained from a known classifier to train an unknown detector with instances of known classes only. Gradients correspond to the amount of model updates required to properly represent a given sample, which we exploit to understand the model's capability to characterize inputs with its learned features. Our approach can be utilized with any classifier trained in a supervised manner on known classes without the need to model the distribution of unknown samples explicitly. We show that our gradient-based approach outperforms state-of-the-art methods by up to 11.6% in open-set classification. | ||