# Video Class Agnostic Segmentation with Contrastive Learning for Autonomous Driving

arXiv: https://arxiv.org/abs/2105.03533 · HTML: https://mlsanity.com/paper/2105.03533/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 27 references that are in the map.
- First posted on arXiv 7 May 2021.

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination](https://mlsanity.com/paper/1805.01978/) (2018)
- [Group Normalization](https://mlsanity.com/paper/1803.08494/) (2018)
- [FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks](https://mlsanity.com/paper/1612.01925/) (2016)
- [PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment](https://mlsanity.com/paper/1908.06391/) (2019)
- [Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networks](https://mlsanity.com/paper/1406.6909/) (2014)
- [DeepDriving: Learning Affordance for Direct Perception in Autonomous Driving](https://mlsanity.com/paper/1505.00256/) (2015)
- [CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learning](https://mlsanity.com/paper/1903.02351/) (2019)
- [Contrastive Training for Improved Out-of-Distribution Detection](https://mlsanity.com/paper/2007.05566/) (2020)
- [Video Panoptic Segmentation](https://mlsanity.com/paper/2006.11339/) (2020)
- [Identifying Unknown Instances for Autonomous Driving](https://mlsanity.com/paper/1910.11296/) (2019)
- [Semantic Video CNNs through Representation Warping](https://mlsanity.com/paper/1708.03088/) (2017)
- [Watching the World Go By: Representation Learning from Unlabeled Videos](https://mlsanity.com/paper/2003.07990/) (2020)
- [Universal Weakly Supervised Segmentation by Pixel-to-Segment Contrastive Learning](https://mlsanity.com/paper/2105.00957/) (2021)
- [4D Generic Video Object Proposals](https://mlsanity.com/paper/1901.09260/) (2019)

## Abstract (arXiv)

Semantic segmentation in autonomous driving predominantly focuses on learning from large-scale data with a closed set of known classes without considering unknown objects. Motivated by safety reasons, we address the video class agnostic segmentation task, which considers unknown objects outside the closed set of known classes in our training data. We propose a novel auxiliary contrastive loss to learn the segmentation of known classes and unknown objects. Unlike previous work in contrastive learning that samples the anchor, positive and negative examples on an image level, our contrastive learning method leverages pixel-wise semantic and temporal guidance. We conduct experiments on Cityscapes-VPS by withholding four classes from training and show an improvement gain for both known and unknown objects segmentation with the auxiliary contrastive loss. We further release a large-scale synthetic dataset for different autonomous driving scenarios that includes distinct and rare unknown objects. We conduct experiments on the full synthetic dataset and a reduced small-scale version, and show how contrastive learning is more effective in small scale datasets. Our proposed models, dataset, and code will be released at https://github.com/MSiam/video_class_agnostic_segmentation.