# Can Unsupervised Segmentation Reduce Annotation Costs for Video Semantic Segmentation?

arXiv: https://arxiv.org/abs/2603.27697 · HTML: https://mlsanity.com/paper/2603.27697/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 42 references that are in the map.
- First posted on arXiv 29 Mar 2026.

## Builds on (most cited first, 29 of 29)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning](https://mlsanity.com/paper/1805.04687/) (2018)
- [Per-Pixel Classification is Not All You Need for Semantic Segmentation](https://mlsanity.com/paper/2107.06278/) (2021)
- [Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs](https://mlsanity.com/paper/1412.7062/) (2014)
- [OneFormer: One Transformer to Rule Universal Image Segmentation](https://mlsanity.com/paper/2211.06220/) (2022)
- [Dilated Residual Networks](https://mlsanity.com/paper/1705.09914/) (2017)
- [Adversarial Learning for Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/1802.07934/) (2018)
- [Semi-Supervised Semantic Segmentation with High- and Low-level Consistency](https://mlsanity.com/paper/1908.05724/) (2019)
- [Improving Semantic Segmentation via Video Propagation and Label Relaxation](https://mlsanity.com/paper/1812.01593/) (2018)
- [Accel: A Corrective Fusion Network for Efficient Semantic Segmentation on Video](https://mlsanity.com/paper/1807.06667/) (2018)
- [Temporally Distributed Networks for Fast Video Semantic Segmentation](https://mlsanity.com/paper/2004.01800/) (2020)
- [Semantic Video Segmentation by Gated Recurrent Flow Propagation](https://mlsanity.com/paper/1612.08871/) (2016)
- [Semantic Video CNNs through Representation Warping](https://mlsanity.com/paper/1708.03088/) (2017)
- [Efficient Semantic Video Segmentation with Per-frame Inference](https://mlsanity.com/paper/2002.11433/) (2020)
- [Low-Latency Video Semantic Segmentation](https://mlsanity.com/paper/1804.00389/) (2018)
- [SeMask: Semantically Masked Transformers for Semantic Segmentation](https://mlsanity.com/paper/2112.12782/) (2021)
- [Temporal Memory Attention for Video Semantic Segmentation](https://mlsanity.com/paper/2102.08643/) (2021)
- [Improving Semantic Segmentation via Self-Training](https://mlsanity.com/paper/2004.14960/) (2020)
- [Surveillance Video Parsing with Single Frame Supervision](https://mlsanity.com/paper/1611.09587/) (2016)
- [GSVNet: Guided Spatially-Varying Convolution for Fast Semantic Segmentation on Video](https://mlsanity.com/paper/2103.08834/) (2021)

## Abstract (arXiv)

Present-day deep neural networks for video semantic segmentation require a large number of fine-grained pixel-level annotations to achieve the best possible results. Obtaining such annotations, however, is very expensive. On the other hand, raw, unannotated video frames are practically free to obtain. Similarly, coarse annotations, which do not require precise boundaries, are also much cheaper. This paper investigates approaches to reduce the annotation cost required for video segmentation datasets by utilising such resources. We show that using state-of-the-art segmentation foundation models, Segment Anything Model (SAM) and Segment Anything Model 2 (SAM 2), we can utilise both unannotated frames as well as coarse annotations to alleviate the effort required for manual annotation of video segmentation datasets by automating mask generation. Our investigation suggests that if used appropriately, we can reduce the need for annotation by a third with similar performance for video semantic segmentation. More significantly, our analysis suggests that the variety of frames in the dataset is more important than the number of frames for obtaining the best performance.