mlsanityData to 14 Oct 2026

Instance-Aware Observer Network for Out-of-Distribution Object Segmentation

arXiv 2207.08782 ↗First posted 18 Jul 2022cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Recent works on predictive uncertainty estimation have shown promising results on Out-Of-Distribution (OOD) detection for semantic segmentation. However, these methods struggle to precisely locate the point of interest in the image, i.e, the anomaly. This limitation is due to the difficulty of finegrained prediction at the pixel level. To address this issue, we build upon the recent ObsNet approach by providing object instance knowledge to the observer. We extend ObsNet by harnessing an instance-wise mask prediction. We use an additional, class agnostic, object detector to filter and aggregate observer predictions. Finally, we predict an unique anomaly score for each instance in the image. We show that our proposed method accurately disentangles in-distribution objects from OOD objects on three datasets.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 52 of its 62 references that are in the map. First posted on arXiv 18 Jul 2022.

Builds on

52 of 62 references.

References · 52

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  3. 2017Mask R-CNNcited by 7,277
  4. 2017On Calibration of Modern Neural Networkscited by 4,960
  5. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  6. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  7. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  8. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,223
  9. 2015SSD: Single Shot MultiBox Detectorcited by 3,130
  10. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  11. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,352
  12. 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,487
38 more
  1. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
  2. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,328
  3. 2018BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learningcited by 1,288
  4. 2018Deep Anomaly Detection with Outlier Exposurecited by 942
  5. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 776
  6. 2017Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discoverycited by 566
  7. 2019A Simple Baseline for Bayesian Uncertainty in Deep Learningcited by 560
  8. 2018Predictive Uncertainty Estimation via Prior Networkscited by 557
  9. 2015Weight Uncertainty in Neural Networkscited by 554
  10. 2020Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awarenesscited by 389
  11. 2020BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learningcited by 371
  12. 2019Learning Loss for Active Learningcited by 336
  13. 2018Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problemcited by 323
  14. 2018Learning Confidence for Out-of-Distribution Detection in Neural Networkscited by 245
  15. 2015Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understandingcited by 218
  16. 2019Addressing Failure Prediction by Learning Model Confidencecited by 186
  17. 2020Efficient and Scalable Bayesian Neural Nets with Rank-1 Factorscited by 171
  18. 2018Deep Autoencoding Models for Unsupervised Anomaly Segmentation in Brain MR Imagescited by 146
  19. 2019Detecting the Unexpected via Image Resynthesiscited by 137
  20. 2019Gaussian YOLOv3: An Accurate and Fast Object Detector Using Localization Uncertainty for Autonomous Drivingcited by 105
  21. 2020Synthesize then Compare: Detecting Failures and Anomalies for Semantic Segmentationcited by 96
  22. 2020Masksembles for Uncertainty Estimationcited by 88
  23. 2021Active Learning for Deep Object Detection via Probabilistic Modelingcited by 79
  24. 2019Sampling-free Epistemic Uncertainty Estimation Using Approximated Variance Propagationcited by 74
  25. 2022Unknown-Aware Object Detection: Learning What You Don't Know from Videos in the Wildcited by 70
  26. 2020Scalable Active Learning for Object Detectioncited by 58
  27. 2019Simultaneous Semantic Segmentation and Outlier Detection in Presence of Domain Shiftcited by 54
  28. 2018Evaluating Merging Strategies for Sampling-based Uncertainty Techniques in Object Detectioncited by 51
  29. 2021Triggering Failures: Out-Of-Distribution detection by learning from local adversarial attacks in Semantic Segmentationcited by 40
  30. 2019TRADI: Tracking deep neural network weight distributions for uncertainty estimationcited by 39
  31. 2021Estimating and Evaluating Regression Predictive Uncertainty in Deep Object Detectorscited by 37
  32. 2015Binary Classifier Calibration using an Ensemble of Near Isotonic Regression Modelscited by 21
  33. 2020Encoding the latent posterior of Bayesian Neural Networks for uncertainty quantificationcited by 18
  34. 2021CertainNet: Sampling-free Uncertainty Estimation for Object Detectioncited by 15
  35. 2018Failure Prediction for Autonomous Drivingcited by 14
  36. 2020Stochastic-YOLO: Efficient Probabilistic Object Detection under Dataset Shiftscited by 9
  37. 2020PEP: Parameter Ensembling by Perturbationcited by 9
  38. 2021Learning Uncertainty For Safety-Oriented Semantic Segmentation In Autonomous Drivingcited by 8

50 most cited of 52 All 52 (JSON)

Built on by

Not cited yet.