CoChat

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

Open access
Badrinarayanan, Vijay, Kendall, Alex, Cipolla, Roberto · 2017 · IEEE Transactions on Pattern Analysis and Machine Intelligence

The DOI matches its Crossref record; 78 of the 78 references it cites were found in a registry or an index.

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 [1] . 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 [2] and also with the well known DeepLab-LargeFOV [3] , DeconvNet [4] 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 and can be trained end-to-end using stochastic gradient descent. We also performed a controlled benchmark of SegNet and other architectures on both road scenes and SUN RGB-D indoor scene segmentation tasks. These quantitative assessments show that SegNet provides good performance with competitive inference time and most 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.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/tpami.2016.2644615

Cites

78 of 78 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 78 references

Research works printed but not linked: 4

  1. grangier, 2009, Deep convolutional networks for scene parsing, Proc ICML Deep Learn Workshop
  2. gal, 2015, Dropout as a Bayesian approximation: Insights and applications, Proc ICML Deep Learn Workshop
  3. 10.1109/ICCV.2015.304 · DOI · Paper page
  4. 10.1109/ICCV.2015.178 · DOI · Paper page

Cited by

Items 901–1,000 of 1,095

Metadata

Authors
Badrinarayanan, V., Kendall, A., & Cipolla, R.
Affiliations
University of Cambridge (GB)
Venue
IEEE Transactions on Pattern Analysis and Machine Intelligence
Published
2017-12-01
Volume
39
Issue
12
Pages
2481-2495
ISSN
  • 0162-8828 (ISSN-L)
  • 2160-9292
  • 1939-3539
OpenAlex
W1910657905
Cited by
19,631
References
74
Citations by year
2026: 1263 · 2025: 2194 · 2024: 2708 · 2023: 2727 · 2022: 2792 · 2021: 2633 · 2020: 2199 · 2019: 1747 · 2018: 935 · 2017: 356
FWCI
594.57
Type
journal article
Language
en
Open access
Locations
  • IEEE Transactions on Pattern Analysis and Machine Intelligence (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • Apollo (University of Cambridge) (submittedVersion, cc-by)
  • Cambridge University Engineering Department Publications Database (submittedVersion)
  • arXiv (Cornell University)
  • Apollo (cc-by)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
  • Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Remote-Sensing Image Classification
Keywords
SegNet, semantic segmentation, pixel classification, encoder-decoder architecture, fully convolutional network, VGG16, memory-efficient inference, scene understanding, road scene segmentation, indoor scene segmentation, SUN RGB-D

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.