# Uncertainty Aware Proposal Segmentation for Unknown Object Detection

arXiv: https://arxiv.org/abs/2111.12866 · HTML: https://mlsanity.com/paper/2111.12866/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 33 references that are in the map.
- First posted on arXiv 25 Nov 2021.

## Builds on (most cited first, 26 of 26)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [Predictive Uncertainty Estimation via Prior Networks](https://mlsanity.com/paper/1802.10501/) (2018)
- [Towards Open Set Deep Networks](https://mlsanity.com/paper/1511.06233/) (2015)
- [Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness](https://mlsanity.com/paper/2006.10108/) (2020)
- [Regularisation of Neural Networks by Enforcing Lipschitz Continuity](https://mlsanity.com/paper/1804.04368/) (2018)
- [Towards Open World Object Detection](https://mlsanity.com/paper/2103.02603/) (2021)
- [Concrete Dropout](https://mlsanity.com/paper/1705.07832/) (2017)
- [UPSNet: A Unified Panoptic Segmentation Network](https://mlsanity.com/paper/1901.03784/) (2019)
- [Detecting the Unexpected via Image Resynthesis](https://mlsanity.com/paper/1904.07595/) (2019)
- [The Fishyscapes Benchmark: Measuring Blind Spots in Semantic Segmentation](https://mlsanity.com/paper/1904.03215/) (2019)
- [Lost and Found: Detecting Small Road Hazards for Self-Driving Vehicles](https://mlsanity.com/paper/1609.04653/) (2016)
- [Pixel-wise Anomaly Detection in Complex Driving Scenes](https://mlsanity.com/paper/2103.05445/) (2021)
- [Standardized Max Logits: A Simple yet Effective Approach for Identifying Unexpected Road Obstacles in Urban-Scene Segmentation](https://mlsanity.com/paper/2107.11264/) (2021)
- [Identifying Unknown Instances for Autonomous Driving](https://mlsanity.com/paper/1910.11296/) (2019)
- [A Dataset for Developing and Benchmarking Active Vision](https://mlsanity.com/paper/1702.08272/) (2017)
- [Real-Time Panoptic Segmentation from Dense Detections](https://mlsanity.com/paper/1912.01202/) (2019)
- [Single-Shot Panoptic Segmentation](https://mlsanity.com/paper/1911.00764/) (2019)
- [Learning Densities in Feature Space for Reliable Segmentation of Indoor Scenes](https://mlsanity.com/paper/1908.00448/) (2019)
- [IMP: Instance Mask Projection for High Accuracy Semantic Segmentation of Things](https://mlsanity.com/paper/1906.06597/) (2019)

## Built on by (most cited first, 6 of 6)

- [Uncertainty-aware Panoptic Segmentation](https://mlsanity.com/paper/2206.14554/) (2022)
- [CRSOT: Cross-Resolution Object Tracking using Unaligned Frame and Event Cameras](https://mlsanity.com/paper/2401.02826/) (2024)
- [Uncertainty-aware LiDAR Panoptic Segmentation](https://mlsanity.com/paper/2210.04472/) (2022)
- [MouseSIS: A Frames-and-Events Dataset for Space-Time Instance Segmentation of Mice](https://mlsanity.com/paper/2409.03358/) (2024)
- [An optimization method for out-of-distribution anomaly detection models](https://mlsanity.com/paper/2302.00939/) (2023)
- [Neural Network Meta Classifier: Improving the Reliability of Anomaly Segmentation](https://mlsanity.com/paper/2412.10765/) (2024)

## Abstract (arXiv)

Recent efforts in deploying Deep Neural Networks for object detection in real world applications, such as autonomous driving, assume that all relevant object classes have been observed during training. Quantifying the performance of these models in settings when the test data is not represented in the training set has mostly focused on pixel-level uncertainty estimation techniques of models trained for semantic segmentation. This paper proposes to exploit additional predictions of semantic segmentation models and quantifying its confidences, followed by classification of object hypotheses as known vs. unknown, out of distribution objects. We use object proposals generated by Region Proposal Network (RPN) and adapt distance aware uncertainty estimation of semantic segmentation using Radial Basis Functions Networks (RBFN) for class agnostic object mask prediction. The augmented object proposals are then used to train a classifier for known vs. unknown objects categories. Experimental results demonstrate that the proposed method achieves parallel performance to state of the art methods for unknown object detection and can also be used effectively for reducing object detectors' false positive rate. Our method is well suited for applications where prediction of non-object background categories obtained by semantic segmentation is reliable.