pith. sign in

arxiv: 1511.00561 · v3 · pith:BM574FUEnew · submitted 2015-11-02 · 💻 cs.CV · cs.LG· cs.NE

SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation

Vijay Badrinarayanan , Alex Kendall , Roberto Cipolla This is my paper
classification 💻 cs.CV cs.LGcs.NE
keywords segnetnetworksegmentationarchitecturearchitecturesdecoderencoderfeature
0
0 comments X
read the original abstract

We present a novel and practical deep fully convolutional neural network architecture for semantic pixel-wise segmentation termed SegNet. This core trainable segmentation engine consists of an encoder network, a corresponding decoder network followed by a pixel-wise classification layer. The architecture of the encoder network is topologically identical to the 13 convolutional layers in the VGG16 network. The role of the decoder network is to map the low resolution encoder feature maps to full input resolution feature maps for pixel-wise classification. The novelty of SegNet lies is in the manner in which the decoder upsamples its lower resolution input feature map(s). Specifically, the decoder uses pooling indices computed in the max-pooling step of the corresponding encoder to perform non-linear upsampling. This eliminates the need for learning to upsample. The upsampled maps are sparse and are then convolved with trainable filters to produce dense feature maps. We compare our proposed architecture with the widely adopted FCN and also with the well known DeepLab-LargeFOV, DeconvNet architectures. This comparison reveals the memory versus accuracy trade-off involved in achieving good segmentation performance. SegNet was primarily motivated by scene understanding applications. Hence, it is designed to be efficient both in terms of memory and computational time during inference. It is also significantly smaller in the number of trainable parameters than other competing architectures. We also performed a controlled benchmark of SegNet and other architectures on both road scenes and SUN RGB-D indoor scene segmentation tasks. We show that SegNet provides good performance with competitive inference time and more efficient inference memory-wise as compared to other architectures. We also provide a Caffe implementation of SegNet and a web demo at http://mi.eng.cam.ac.uk/projects/segnet/.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 11 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. SegRAG: Training-Free Retrieval-Augmented Semantic Segmentation

    cs.CV 2026-05 unverdicted novelty 6.0

    SegRAG is a training-free retrieval-augmented framework that extracts class-specific point prompts from a filtered DINOv3 feature bank to boost SAM3 semantic segmentation performance on standard and agricultural benchmarks.

  2. SegRAG: Training-Free Retrieval-Augmented Semantic Segmentation

    cs.CV 2026-05 unverdicted novelty 6.0

    SegRAG augments SAM3 with class-specific point prompts retrieved via DINOv3 features and filtered by ICCD, using TSG at inference to improve open-vocabulary segmentation.

  3. Segmenting Objects in Day and Night:Edge-Conditioned CNN for Thermal Image Semantic Segmentation

    cs.CV 2019-07 unverdicted novelty 6.0

    EC-CNN uses a gated feature-wise transform to incorporate edge priors for thermal semantic segmentation and introduces the SODA dataset of over 7,000 labeled thermal images.

  4. Rethinking Atrous Convolution for Semantic Image Segmentation

    cs.CV 2017-06 unverdicted novelty 6.0

    DeepLabv3 improves semantic segmentation by capturing multi-scale context with cascaded or parallel atrous convolutions and adding global context to ASPP, achieving better results on PASCAL VOC 2012 without DenseCRF p...

  5. The Ethical Dilemma when (not) Setting up Cost-based Decision Rules in Semantic Segmentation

    cs.CV 2019-07 unverdicted novelty 5.0

    Defining egoistic and altruistic cost functions for class confusions in semantic segmentation changes precision, recall, and segment-wise error rates relative to standard MAP decisions.

  6. Semantic-Topological Graph Reasoning for Language-Guided Pulmonary Screening

    cs.CV 2026-04 unverdicted novelty 4.0

    STGR framework integrates LLaMA-3-V and MedSAM via text-to-vision distillation and graph reasoning, achieving 81.5% DSC on LIDC-IDRI with under 1% parameter updates and high cross-fold stability.

  7. Deep inspection: an electrical distribution pole parts study via deep neural networks

    cs.CV 2019-07 unverdicted novelty 4.0

    A two-stage zoom-in detection framework with resampling and reweighting schemes improves detection performance on tiny pole parts in imbalanced aerial image datasets over baseline methods.

  8. SAN: Scale-Aware Network for Semantic Segmentation of High-Resolution Aerial Images

    cs.CV 2019-07 unverdicted novelty 4.0

    SANet adds a re-sampling-based scale-aware module to semantic segmentation networks to better handle inconsistent object scales in aerial images.

  9. Dealing with Topological Information within a Fully Convolutional Neural Network

    cs.CV 2019-06 unverdicted novelty 4.0

    A geodesic operator pre-processing step is introduced to let FCNs exploit topological information for segmenting histological images of pigmented reconstructed epidermis.

  10. ESNet: An Efficient Symmetric Network for Real-time Semantic Segmentation

    cs.CV 2019-06 unverdicted novelty 4.0

    ESNet is a lightweight symmetric CNN using factorized residual units and parallel dilated convolutions that reaches over 62 FPS semantic segmentation on Cityscapes with 1.6M parameters.

  11. A Regularized Convolutional Neural Network for Semantic Image Segmentation

    cs.CV 2019-06 unverdicted novelty 3.0

    Integrating total variation regularization into U-Net and SegNet yields segmentation results with improved spatial regularity and noise robustness on WBC, CamVid, and SUN-RGBD datasets.