Class and Region-Adaptive Constraints for Network Calibration

• Main Authors: Murugesan, Balamurali, Silva-Rodriguez, Julio, Ayed, Ismail Ben, Dolz, Jose
• Format: Journal Article
• Language: English
• Published: 18-03-2024
• Subjects: Computer Science - Computer Vision and Pattern Recognition
• DOI: 10.48550/arxiv.2403.12364

In this work, we present a novel approach to calibrate segmentation networks
that considers the inherent challenges posed by different categories and object
regions. In particular, we present a formulation that integrates class and
region-wise constraints into the learning objective, with multiple penalty
weights to account for class and region differences. Finding the optimal
penalty weights manually, however, might be unfeasible, and potentially hinder
the optimization process. To overcome this limitation, we propose an approach
based on Class and Region-Adaptive constraints (CRaC), which allows to learn
the class and region-wise penalty weights during training. CRaC is based on a
general Augmented Lagrangian method, a well-established technique in
constrained optimization. Experimental results on two popular segmentation
benchmarks, and two well-known segmentation networks, demonstrate the
superiority of CRaC compared to existing approaches. The code is available at:
https://github.com/Bala93/CRac/