Uncertainty-aware Continuous Implicit Neural Representations for Remote Sensing Object Counting
Journal Article
·
· Proceedings of the International Workshop on Artificial Intelligence and Statistics
OSTI ID:2481972
- Texas A & M Univ., College Station, TX (United States)
- Texas A & M Univ., College Station, TX (United States); Brookhaven National Laboratory (BNL), Upton, NY (United States)
Many existing object counting methods rely on density map estimation (DME) of the discrete grid representation by decoding extracted image semantic features from designed convolutional neural networks (CNNs). Relying on discrete density maps not only leads to information loss dependent on the original image resolution, but also has a scalability issue when analyzing high-resolution images with cubically increasing memory complexity. Furthermore, none of the existing methods can offer reliable uncertainty quantification (UQ) for the derived count estimates. To overcome these limitations, we design UNcertainty-aware, hypernetwork-based Implicit neural representations for Counting (UNIC) to assign probabilities and the corresponding counting confidence over continuous spatial coordinates. We derive a sampling-based Bayesian counting loss function and develop the corresponding model training algorithm. UNIC outperforms existing methods on the Remote Sensing Object Counting (RSOC) dataset with reliable UQ and improved interpretability of the derived count estimates. Our code is available at https://github.com/SiyuanXu-tamu/UNIC.
- Research Organization:
- Brookhaven National Laboratory (BNL), Upton, NY (United States)
- Sponsoring Organization:
- USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR); National Science Foundation (NSF)
- Grant/Contract Number:
- SC0012704
- OSTI ID:
- 2481972
- Report Number(s):
- BNL--226387-2024-JAAM
- Journal Information:
- Proceedings of the International Workshop on Artificial Intelligence and Statistics, Journal Name: Proceedings of the International Workshop on Artificial Intelligence and Statistics Vol. 238; ISSN 1525-531X
- Publisher:
- Proceedings of Machine Learning Research (PMLR)Copyright Statement
- Country of Publication:
- United States
- Language:
- English
Similar Records
We Know Where We Don't Know: 3D Bayesian CNNs for Credible Geometric Uncertainty
Technical Report
·
Thu Mar 19 00:00:00 EDT 2020
·
OSTI ID:1605518