Masked Gamma-SSL: Learning Uncertainty Estimation via Masked Image Modeling

2024/02/27 by David Williams, Matthew Gadd, Williams, David S. W. +5
Computer Science · Engineering · #Anomaly Detection Techniques and Applications #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Fault Detection and Control Systems #Machine Learning and Algorithms #Robotics (cs.RO)

paper · pdf · doi:10.48550/arxiv.2402.17622

openalex publication_date 2024/02/27 · openalex created_date 2024/03/05 · openalex updated_date 2026/07/28

Abstract

This work proposes a semantic segmentation network that produces high-quality uncertainty estimates in a single forward pass. We exploit general representations from foundation models and unlabelled datasets through a Masked Image Modeling (MIM) approach, which is robust to augmentation hyper-parameters and simpler than previous techniques. For neural networks used in safety-critical applications, bias in the training data can lead to errors; therefore it is crucial to understand a network's limitations at run time and act accordingly. To this end, we test our proposed method on a number of test domains including the SAX Segmentation benchmark, which includes labelled test data from dense urban, rural and off-road driving domains. The proposed method consistently outperforms uncertainty estimation and Out-of-Distribution (OoD) techniques on this difficult benchmark.

Related

• Mitigating Distributional Shift in Semantic Segmentation via Uncertainty Estimation from Unlabelled Data
• Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness
• Learning Uncertainty For Safety-Oriented Semantic Segmentation In\n Autonomous Driving
• Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding
• A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awareness