# Naive-Student: Leveraging Semi-Supervised Learning in Video Sequences for Urban Scene Segmentation

arXiv: https://arxiv.org/abs/2005.10266 · HTML: https://mlsanity.com/paper/2005.10266/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 May 2020.

## Built on by (most cited first, 30 of 38)

- [Extract Free Dense Labels from CLIP](https://mlsanity.com/paper/2112.01071/) (2021)
- [Self-supervised Augmentation Consistency for Adapting Semantic Segmentation](https://mlsanity.com/paper/2105.00097/) (2021)
- [A Survey on Deep Learning Technique for Video Segmentation](https://mlsanity.com/paper/2107.01153/) (2021)
- [A Simple Baseline for Semi-supervised Semantic Segmentation with Strong Data Augmentation](https://mlsanity.com/paper/2104.07256/) (2021)
- [Re-distributing Biased Pseudo Labels for Semi-supervised Semantic Segmentation: A Baseline Investigation](https://mlsanity.com/paper/2107.11279/) (2021)
- [DOC2PPT: Automatic Presentation Slides Generation from Scientific Documents](https://mlsanity.com/paper/2101.11796/) (2021)
- [Semi-supervised Semantic Segmentation with Error Localization Network](https://mlsanity.com/paper/2204.02078/) (2022)
- [Unsupervised Semantic Segmentation with Self-supervised Object-centric Representations](https://mlsanity.com/paper/2207.05027/) (2022)
- [Scalable Scene Flow from Point Clouds in the Real World](https://mlsanity.com/paper/2103.01306/) (2021)
- [Look Closer to Segment Better: Boundary Patch Refinement for Instance Segmentation](https://mlsanity.com/paper/2104.05239/) (2021)
- [PolyphonicFormer: Unified Query Learning for Depth-aware Video Panoptic Segmentation](https://mlsanity.com/paper/2112.02582/) (2021)
- [Pseudo-labeling for Scalable 3D Object Detection](https://mlsanity.com/paper/2103.02093/) (2021)
- [AuxAdapt: Stable and Efficient Test-Time Adaptation for Temporally Consistent Video Semantic Segmentation](https://mlsanity.com/paper/2110.12369/) (2021)
- [Instance-wise Occlusion and Depth Orders in Natural Scenes](https://mlsanity.com/paper/2111.14562/) (2021)
- [Video Mask Transfiner for High-Quality Video Instance Segmentation](https://mlsanity.com/paper/2207.14012/) (2022)
- [Multimodal Knowledge Expansion](https://mlsanity.com/paper/2103.14431/) (2021)
- [Decoupled Multi-task Learning with Cyclical Self-Regulation for Face Parsing](https://mlsanity.com/paper/2203.14448/) (2022)
- [Exploring Event-driven Dynamic Context for Accident Scene Segmentation](https://mlsanity.com/paper/2112.05006/) (2021)
- [Domain Adaptive Video Segmentation via Temporal Consistency Regularization](https://mlsanity.com/paper/2107.11004/) (2021)
- [Pseudo-label refinement using superpixels for semi-supervised brain tumour segmentation](https://mlsanity.com/paper/2110.08589/) (2021)
- [DSC-PoseNet: Learning 6DoF Object Pose Estimation via Dual-scale Consistency](https://mlsanity.com/paper/2104.03658/) (2021)
- [PanopticDepth: A Unified Framework for Depth-aware Panoptic Segmentation](https://mlsanity.com/paper/2206.00468/) (2022)
- [Robust Mutual Learning for Semi-supervised Semantic Segmentation](https://mlsanity.com/paper/2106.00609/) (2021)
- [kMaX-DeepLab: k-means Mask Transformer](https://mlsanity.com/paper/2207.04044/) (2022)
- [Domain Adaptive Video Segmentation via Temporal Pseudo Supervision](https://mlsanity.com/paper/2207.02372/) (2022)
- [Urban Scene Semantic Segmentation with Low-Cost Coarse Annotation](https://mlsanity.com/paper/2212.07911/) (2022)
- [Global Aggregation then Local Distribution for Scene Parsing](https://mlsanity.com/paper/2107.13154/) (2021)
- [MonoDVPS: A Self-Supervised Monocular Depth Estimation Approach to Depth-aware Video Panoptic Segmentation](https://mlsanity.com/paper/2210.07577/) (2022)
- [PseudoAugment: Learning to Use Unlabeled Data for Data Augmentation in Point Clouds](https://mlsanity.com/paper/2210.13428/) (2022)
- [Mask-based Data Augmentation for Semi-supervised Semantic Segmentation](https://mlsanity.com/paper/2101.10156/) (2021)

## Abstract (arXiv)

Supervised learning in large discriminative models is a mainstay for modern computer vision. Such an approach necessitates investing in large-scale human-annotated datasets for achieving state-of-the-art results. In turn, the efficacy of supervised learning may be limited by the size of the human annotated dataset. This limitation is particularly notable for image segmentation tasks, where the expense of human annotation is especially large, yet large amounts of unlabeled data may exist. In this work, we ask if we may leverage semi-supervised learning in unlabeled video sequences and extra images to improve the performance on urban scene segmentation, simultaneously tackling semantic, instance, and panoptic segmentation. The goal of this work is to avoid the construction of sophisticated, learned architectures specific to label propagation (e.g., patch matching and optical flow). Instead, we simply predict pseudo-labels for the unlabeled data and train subsequent models with both human-annotated and pseudo-labeled data. The procedure is iterated for several times. As a result, our Naive-Student model, trained with such simple yet effective iterative semi-supervised learning, attains state-of-the-art results at all three Cityscapes benchmarks, reaching the performance of 67.8% PQ, 42.6% AP, and 85.2% mIOU on the test set. We view this work as a notable step towards building a simple procedure to harness unlabeled video sequences and extra images to surpass state-of-the-art performance on core computer vision tasks.