# SegNet: A Deep Convolutional Encoder-Decoder Architecture for Robust Semantic Pixel-Wise Labelling

arXiv: https://arxiv.org/abs/1505.07293 · HTML: https://mlsanity.com/paper/1505.07293/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 May 2015.

## Built on by (most cited first, 30 of 37)

- [SAM2-Adapter: Evaluating & Adapting Segment Anything 2 in Downstream Tasks: Camouflage, Shadow, Medical Image Segmentation, and More](https://mlsanity.com/paper/2408.04579/) (2024)
- [Progressive Semantic Segmentation](https://mlsanity.com/paper/2104.03778/) (2021)
- [Meta-UDA: Unsupervised Domain Adaptive Thermal Object Detection using Meta-Learning](https://mlsanity.com/paper/2110.03143/) (2021)
- [DeepSSM: A Blueprint for Image-to-Shape Deep Learning Models](https://mlsanity.com/paper/2110.07152/) (2021)
- [Single Frame Semantic Segmentation Using Multi-Modal Spherical Images](https://mlsanity.com/paper/2308.09369/) (2023)
- [Revisiting Crowd Counting: State-of-the-art, Trends, and Future Perspectives](https://mlsanity.com/paper/2209.07271/) (2022)
- [Certified Zeroth-order Black-Box Defense with Robust UNet Denoiser](https://mlsanity.com/paper/2304.06430/) (2023)
- [ATLANTIS: A Benchmark for Semantic Segmentation of Waterbody Images](https://mlsanity.com/paper/2111.11567/) (2021)
- [Probabilistic Graph Attention Network with Conditional Kernels for Pixel-Wise Prediction](https://mlsanity.com/paper/2101.02843/) (2021)
- [Zero-Shot Segmentation of Eye Features Using the Segment Anything Model (SAM)](https://mlsanity.com/paper/2311.08077/) (2023)
- [SERNet-Former: Semantic Segmentation by Efficient Residual Network with Attention-Boosting Gates and Attention-Fusion Networks](https://mlsanity.com/paper/2401.15741/) (2024)
- [LMBiS-Net: A Lightweight Multipath Bidirectional Skip Connection based CNN for Retinal Blood Vessel Segmentation](https://mlsanity.com/paper/2309.04968/) (2023)
- [A Specific Task-oriented Semantic Image Communication System for substation patrol inspection](https://mlsanity.com/paper/2301.03331/) (2023)
- [WCEbleedGen: A wireless capsule endoscopy dataset and its benchmarking for automatic bleeding classification, detection, and segmentation](https://mlsanity.com/paper/2408.12466/) (2024)
- [Automatic Semantic Segmentation of the Lumbar Spine: Clinical Applicability in a Multi-parametric and Multi-centre Study on Magnetic Resonance Images](https://mlsanity.com/paper/2111.08712/) (2021)
- [Transformer-based Flood Scene Segmentation for Developing Countries](https://mlsanity.com/paper/2210.04218/) (2022)
- [3DS-SLAM: A 3D Object Detection based Semantic SLAM towards Dynamic Indoor Environments](https://mlsanity.com/paper/2310.06385/) (2023)
- [Segmenting Object Affordances: Reproducibility and Sensitivity to Scale](https://mlsanity.com/paper/2409.01814/) (2024)
- [Variational Structured Attention Networks for Deep Visual Representation Learning](https://mlsanity.com/paper/2103.03510/) (2021)
- [Image Processing Methods for Coronal Hole Segmentation, Matching, and Map Classification](https://mlsanity.com/paper/2201.01380/) (2022)
- [Search for Concepts: Discovering Visual Concepts Using Direct Optimization](https://mlsanity.com/paper/2210.14808/) (2022)
- [Quantifying Model Uncertainty for Semantic Segmentation using Operators in the RKHS](https://mlsanity.com/paper/2211.01999/) (2022)
- [FPGA-Based Neural Network Accelerators for Space Applications: A Survey](https://mlsanity.com/paper/2504.16173/) (2025)
- [CASPIANET++: A Multidimensional Channel-Spatial Asymmetric Attention Network with Noisy Student Curriculum Learning Paradigm for Brain Tumor Segmentation](https://mlsanity.com/paper/2107.04099/) (2021)
- [Bend-Net: Bending Loss Regularized Multitask Learning Network for Nuclei Segmentation in Histopathology Images](https://mlsanity.com/paper/2109.15283/) (2021)
- [Magnetic Field Prediction Using Generative Adversarial Networks](https://mlsanity.com/paper/2203.07897/) (2022)
- [S-R2F2U-Net: A single-stage model for teeth segmentation](https://mlsanity.com/paper/2204.02939/) (2022)
- [Building Footprint Extraction with Graph Convolutional Network](https://mlsanity.com/paper/2305.04499/) (2023)
- [Visual Affordance Prediction: Survey and Reproducibility](https://mlsanity.com/paper/2505.05074/) (2025)
- [Learning Neural Parsers with Deterministic Differentiable Imitation Learning](https://mlsanity.com/paper/1806.07822/) (2018)

## Abstract (arXiv)

We propose a novel deep architecture, SegNet, for semantic pixel wise image labelling. SegNet has several attractive properties; (i) it only requires forward evaluation of a fully learnt function to obtain smooth label predictions, (ii) with increasing depth, a larger context is considered for pixel labelling which improves accuracy, and (iii) it is easy to visualise the effect of feature activation(s) in the pixel label space at any depth. SegNet is composed of a stack of encoders followed by a corresponding decoder stack which feeds into a soft-max classification layer. The decoders help map low resolution feature maps at the output of the encoder stack to full input image size feature maps. This addresses an important drawback of recent deep learning approaches which have adopted networks designed for object categorization for pixel wise labelling. These methods lack a mechanism to map deep layer feature maps to input dimensions. They resort to ad hoc methods to upsample features, e.g. by replication. This results in noisy predictions and also restricts the number of pooling layers in order to avoid too much upsampling and thus reduces spatial context. SegNet overcomes these problems by learning to map encoder outputs to image pixel labels. We test the performance of SegNet on outdoor RGB scenes from CamVid, KITTI and indoor scenes from the NYU dataset. Our results show that SegNet achieves state-of-the-art performance even without use of additional cues such as depth, video frames or post-processing with CRF models.