Probing Contextual Diversity for Dense Out-of-Distribution Detection
Not on the map. Why?
Abstract (arXiv)
Detection of out-of-distribution (OoD) samples in the context of image classification has recently become an area of interest and active study, along with the topic of uncertainty estimation, to which it is closely related. In this paper we explore the task of OoD segmentation, which has been studied less than its classification counterpart and presents additional challenges. Segmentation is a dense prediction task for which the model's outcome for each pixel depends on its surroundings. The receptive field and the reliance on context play a role for distinguishing different classes and, correspondingly, for spotting OoD entities. We introduce MOoSe, an efficient strategy to leverage the various levels of context represented within semantic segmentation models and show that even a simple aggregation of multi-scale representations has consistently positive effects on OoD detection and uncertainty estimation.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 56 of its 65 references that are in the map. First posted on arXiv 30 Aug 2022.
Builds on
56 of 65 references.
References · 56
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2017On Calibration of Modern Neural Networkscited by 4,960
- 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
- 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
- 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
- 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
- 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,223
- 2016Pyramid Scene Parsing Networkcited by 2,479
- 2017CARLA: An Open Urban Driving Simulatorcited by 2,449
- 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
- 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,161
- 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
38 more
- 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,328
- 2018Deep Anomaly Detection with Outlier Exposurecited by 942
- 2020A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challengescited by 819
- 2017Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discoverycited by 566
- 2019Using Self-Supervised Learning Can Improve Model Robustness and Uncertaintycited by 514
- 2019Scaling Out-of-Distribution Detection for Real-World Settingscited by 465
- 2018Do Deep Generative Models Know What They Don't Know?cited by 443
- 2019Panoptic-DeepLabcited by 363
- 2018Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problemcited by 323
- 2020Sub-Image Anomaly Detection with Deep Pyramid Correspondencescited by 300
- 2018Deep Anomaly Detection Using Geometric Transformationscited by 269
- 2020Why Normalizing Flows Fail to Detect Out-of-Distribution Datacited by 221
- 2015Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understandingcited by 218
- 2020Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flowscited by 212
- 2020Classification-Based Anomaly Detection for General Datacited by 211
- 2020Contrastive Training for Improved Out-of-Distribution Detectioncited by 186
- 2018Understanding Measures of Uncertainty for Adversarial Example Detectioncited by 177
- 2019Ensemble Distribution Distillationcited by 158
- 2021SegmentMeIfYouCan: A Benchmark for Anomaly Segmentationcited by 150
- 2018Deep Autoencoding Models for Unsupervised Anomaly Segmentation in Brain MR Imagescited by 146
- 2015Why M Heads are Better than One: Training a Diverse Ensemble of Deep Networkscited by 139
- 2019Detecting the Unexpected via Image Resynthesiscited by 137
- 2018Uncertainty Estimates and Multi-Hypotheses Networks for Optical Flowcited by 135
- 2021OpenGAN: Open-Set Recognition via Open Data Generationcited by 135
- 2020Entropy Maximization and Meta Classification for Out-Of-Distribution Detection in Semantic Segmentationcited by 133
- 2018Out-of-Distribution Detection Using an Ensemble of Self Supervised Leave-out Classifierscited by 126
- 2019The Fishyscapes Benchmark: Measuring Blind Spots in Semantic Segmentationcited by 122
- 2016Lost and Found: Detecting Small Road Hazards for Self-Driving Vehiclescited by 117
- 2020Hybrid Models for Open Set Recognitioncited by 109
- 2021Pixel-wise Anomaly Detection in Complex Driving Scenescited by 109
- 2020Synthesize then Compare: Detecting Failures and Anomalies for Semantic Segmentationcited by 96
- 2021Standardized Max Logits: A Simple yet Effective Approach for Identifying Unexpected Road Obstacles in Urban-Scene Segmentationcited by 77
- 2020Understanding Anomaly Detection with Deep Invertible Networks through Hierarchies of Distributions and Featurescited by 64
- 2019Simultaneous Semantic Segmentation and Outlier Detection in Presence of Domain Shiftcited by 54
- 2021Deep Metric Learning for Open World Semantic Segmentationcited by 51
- 2021Triggering Failures: Out-Of-Distribution detection by learning from local adversarial attacks in Semantic Segmentationcited by 40
- 2019TRADI: Tracking deep neural network weight distributions for uncertainty estimationcited by 39
- 2022Lawin Transformer: Improving Semantic Segmentation Transformer with Multi-Scale Representations via Large Window Attentioncited by 30
50 most cited of 56 All 56 (JSON)
Built on by
Citing papers per year: 2022: 1; 2023: 1; 2024: 1.
3 papers.