Masked Gamma-SSL: Learning Uncertainty Estimation via Masked Image Modeling
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 33 of its 40 references that are in the map. First posted on arXiv 27 Feb 2024.
Builds on
33 of 40 references.
References · 33
- 2017Attention Is All You Needcited by 59,932
- 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
- 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
- 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
- 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
- 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
- 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
- 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
- 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
- 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
- 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
- 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,338
21 more
- 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
- 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
- 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
- 2018BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learningcited by 1,282
- 2018Deep Anomaly Detection with Outlier Exposurecited by 939
- 2016Deep Variational Information Bottleneckcited by 915
- 2021iBOT: Image BERT Pre-Training with Online Tokenizercited by 891
- 2018Predictive Uncertainty Estimation via Prior Networkscited by 555
- 2022ViM: Out-Of-Distribution with Virtual-logit Matchingcited by 404
- 2017Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samplescited by 389
- 2020Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awarenesscited by 389
- 2017Multiplicative Normalizing Flows for Variational Bayesian Neural Networkscited by 157
- 2021Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samplescited by 114
- 2022SemMAE: Semantic-Guided Masking for Learning Masked Autoencoderscited by 113
- 2022Adversarial Masking for Self-Supervised Learningcited by 78
- 2018Lightweight Probabilistic Deep Networkscited by 77
- 2019Sampling-free Epistemic Uncertainty Estimation Using Approximated Variance Propagationcited by 74
- 2018Uncertainty in the Variational Information Bottleneckcited by 39
- 2020Uncertainty Estimation Using a Single Deep Deterministic Neural Networkcited by 37
- 2018Probably Unknown: Deep Inverse Sensor Modelling In Radarcited by 16
- 2021Fool Me Once: Robust Selective Segmentation via Out-of-Distribution Detection with Contrastive Learningcited by 9
Built on by
Citing papers per year: 2024: 1.
1 paper.