Methods › Computer Vision › Semantic Segmentation Models › PSPNet
PSPNet
Introduced by Hengshuang Zhao et al. in Pyramid Scene Parsing Network
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
PSPNet, or Pyramid Scene Parsing Network, is a semantic segmentation model that utilises a pyramid parsing module that exploits global context information by different-region based context aggregation. The local and global clues together make the final prediction more reliable. We also propose an optimization
Given an input image, PSPNet use a pretrained CNN with the dilated network strategy to extract the feature map. The final feature map size is 1/8 of the input image. On top of the map, we use the pyramid pooling module to gather context information. Using our 4-level pyramid, the pooling kernels cover the whole, half of, and small portions of the image. They are fused as the global prior. Then we concatenate the prior with the original feature map in the final part of. It is followed by a convolution layer to generate the final prediction map.
In Syntology name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
Papers archive 2025-07-28
archive papers tagged: 47 · with a code link: 21 · where Syntology ran a sample: 2 (2 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (2 of 47 tagged: 2 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 47 of 47, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
Semantic segmentation for building houses from wooden cubes 28 Mar 2025 · 0 repositories · arXiv:2503.22125
-
Optimized Unet with Attention Mechanism for Multi-Scale Semantic Segmentation 6 Feb 2025 · 0 repositories · arXiv:2502.03813
-
Parking Space Detection in the City of Granada 11 Jan 2025 · 1 repository · arXiv:2501.06651
-
Hyperspectral Imaging-Based Perception in Autonomous Driving Scenarios: Benchmarking Baseline Semantic Segmentation Models 29 Oct 2024 · 1 repository · arXiv:2410.22101
-
A Surprisingly Simple Approach to Generalized Few-Shot Semantic Segmentation 26 Sep 2024 · 1 repository
-
A Comparative Analysis of CNN-based Deep Learning Models for Landslide Detection 3 Aug 2024 · 0 repositories · arXiv:2408.01692
-
Make a Strong Teacher with Label Assistance: A Novel Knowledge Distillation Approach for Semantic Segmentation 18 Jul 2024 · 1 repository · arXiv:2407.13254
-
Evaluation of Deep Learning Semantic Segmentation for Land Cover Mapping on Multispectral, Hyperspectral and High Spatial Aerial Imagery 20 Jun 2024 · 0 repositories · arXiv:2406.14220
-
Fuzzy Rank-based Late Fusion Technique for Cytology image Segmentation 16 Mar 2024 · 0 repositories · arXiv:2403.10884
-
Generative Denoise Distillation: Simple Stochastic Noises Induce Efficient Knowledge Transfer for Dense Prediction 16 Jan 2024 · 1 repository · arXiv:2401.08332
-
A knowledge-based data-driven (KBDD) framework for all-day identification of cloud types using satellite remote sensing 1 Dec 2023 · 0 repositories · arXiv:2312.00308
-
Equirectangular image construction method for standard CNNs for Semantic Segmentation 13 Oct 2023 · 0 repositories · arXiv:2310.09122
-
Evaluation Kidney Layer Segmentation on Whole Slide Imaging using Convolutional Neural Networks and Transformers 5 Sep 2023 · 0 repositories · arXiv:2309.02563
-
Image Segmentation Keras : Implementation of Segnet, FCN, UNet, PSPNet and other models in Keras 25 Jul 2023 · 2 repositories · arXiv:2307.13215
-
SSSegmenation: An Open Source Supervised Semantic Segmentation Toolbox Based on PyTorch 26 May 2023 · 1 repository · arXiv:2305.17091
-
A Simple and Generic Framework for Feature Distillation via Channel-wise Transformation 23 Mar 2023 · 0 repositories · arXiv:2303.13212
-
An End-to-End Two-Phase Deep Learning-Based workflow to Segment Man-made Objects Around Reservoirs 7 Feb 2023 · 0 repositories · arXiv:2302.03282
-
Efficient and Effective Methods for Mixed Precision Neural Network Quantization for Faster, Energy-efficient Inference 30 Jan 2023 · 0 repositories · arXiv:2301.13330
-
A Strong Baseline for Generalized Few-Shot Semantic Segmentation 25 Nov 2022 · 2 repositories · arXiv:2211.14126
-
Road Rutting Detection using Deep Learning on Images 28 Sep 2022 · 0 repositories · arXiv:2209.14225
-
MassMIND: Massachusetts Maritime INfrared Dataset 9 Sep 2022 · 1 repository · arXiv:2209.04097
-
Landslide4Sense: Reference Benchmark Data and Deep Learning Models for Landslide Detection 1 Jun 2022 · 0 repositories · arXiv:2206.00515
-
Learning What Not to Segment: A New Perspective on Few-Shot Segmentation 15 Mar 2022 · 1 repository · arXiv:2203.07615Syntology official (archive's flag): 16 ran · 16 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 10 where Syntology's instrument failed) · 1 unverified (of 17 harvested samples) · 11 pointer-only (licence)
-
Boosting Mask R-CNN Performance for Long, Thin Forensic Traces with Pre-Segmentation and IoU Region Merging 8 Mar 2022 · 0 repositories · arXiv:2203.03886
-
MSP : Refine Boundary Segmentation via Multiscale Superpixel 3 Dec 2021 · 0 repositories · arXiv:2112.01746
-
Utilizing Attention, Linked Blocks, And Pyramid Pooling To Propel Brain Tumor Segmentation In 3D 29 Sep 2021 · 1 repository
-
Mining Contextual Information Beyond Image for Semantic Segmentation 26 Aug 2021 · 1 repository · arXiv:2108.11819Syntology official: harvested, nothing ran · 0 ran · 2 unverified (of 2 harvested samples)
-
Woodscape Fisheye Semantic Segmentation for Autonomous Driving -- CVPR 2021 OmniCV Workshop Challenge 17 Jul 2021 · 0 repositories · arXiv:2107.08246
-
Encoder-Decoder Architectures for Clinically Relevant Coronary Artery Segmentation 21 Jun 2021 · 1 repository · arXiv:2106.11447
-
Analyzing Green View Index and Green View Index best path using Google Street View and deep learning 26 Apr 2021 · 1 repository · arXiv:2104.12627
-
Cross-Dataset Collaborative Learning for Semantic Segmentation in Autonomous Driving 21 Mar 2021 · 0 repositories · arXiv:2103.11351
-
Scale-aware Neural Network for Semantic Segmentation of Multi-resolution Remote Sensing Images 14 Mar 2021 · 0 repositories · arXiv:2103.07935
-
Local Memory Attention for Fast Video Semantic Segmentation 5 Jan 2021 · 1 repository · arXiv:2101.01715
-
Full-Glow: Fully conditional Glow for more realistic image generation 10 Dec 2020 · 1 repository · arXiv:2012.05846
-
Automatic Quantification of Settlement Damage using Deep Learning of Satellite Images 12 Oct 2020 · 0 repositories · arXiv:2010.05512
-
SESV: Accurate Medical Image Segmentation byPredicting and Correcting Errors 21 Sep 2020 · 0 repositories
-
Multi-Attention-Network for Semantic Segmentation of Fine Resolution Remote Sensing Images 3 Sep 2020 · 0 repositories · arXiv:2009.02130
-
Exploiting the Transferability of Deep Learning Systems Across Multi-modal Retinal Scans for Extracting Retinopathy Lesions 4 Jun 2020 · 0 repositories · arXiv:2006.02662
-
A New Multiple Max-pooling Integration Module and Cross Multiscale Deconvolution Network Based on Image Semantic Segmentation 25 Mar 2020 · 0 repositories · arXiv:2003.11213
-
Efficacy of Pixel-Level OOD Detection for Semantic Segmentation 7 Nov 2019 · 0 repositories · arXiv:1911.02897
-
Automated Deep Photo Style Transfer 12 Jan 2019 · 1 repository · arXiv:1901.03915
-
Impact of Ground Truth Annotation Quality on Performance of Semantic Image Segmentation of Traffic Conditions 30 Dec 2018 · 1 repository · arXiv:1901.00001
-
ShelfNet for Fast Semantic Segmentation 27 Nov 2018 · 6 repositories · arXiv:1811.11254
-
OCNet: Object Context Network for Scene Parsing 4 Sep 2018 · 8 repositories · arXiv:1809.00916
-
Dermoscopic Image Analysis for ISIC Challenge 2018 24 Jul 2018 · 0 repositories · arXiv:1807.08948
-
Performance Evaluation of Deep Learning Networks for Semantic Segmentation of Traffic Stereo-Pair Images 5 Jun 2018 · 0 repositories · arXiv:1806.01896
-
Pyramid Scene Parsing Network 4 Dec 2016 · 67 repositories · arXiv:1612.01105Syntology community repositories only · 21 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 7 where Syntology's instrument failed) · 8 unverified (of 29 harvested samples) · 5 pointer-only (licence)
Tasks archive 2025-07-28
20 shown of 54 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections