{"url":"/method/pspnet","slug":"pspnet","name":"PSPNet","full_name":"PSPNet","full_name_withheld":false,"description_markdown":"**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\r\n\r\nGiven 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](https://paperswithcode.com/method/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.\r\nThen we concatenate the prior with the original feature map in the final part of. It is followed by a [convolution](https://paperswithcode.com/method/convolution) layer to generate the final prediction map.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Pyramid Scene Parsing Network","paper":"/paper/pyramid-scene-parsing-network","first_author":"Hengshuang Zhao","n_authors":5,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/pyramid-scene-parsing-network"},"source":{"url":"http://arxiv.org/abs/1612.01105v2","title":"Pyramid Scene Parsing Network","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/xitongpu/PSPNet","code_snippet_url_on_a_code_host":true,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Semantic Segmentation Models","url":"/methods/category/semantic-segmentation-models","pwc_aliases":["segmentation-models"]}],"n_papers_tagged":47,"archive_num_papers":47,"papers_newest_first":[{"paper":null,"title":"Semantic segmentation for building houses from wooden cubes","date":"2025-03-28","arxiv_id":"2503.22125","n_code_links":0,"syntology":null},{"paper":null,"title":"Optimized Unet with Attention Mechanism for Multi-Scale Semantic Segmentation","date":"2025-02-06","arxiv_id":"2502.03813","n_code_links":0,"syntology":null},{"paper":"/paper/parking-space-detection-in-the-city-of","title":"Parking Space Detection in the City of Granada","date":"2025-01-11","arxiv_id":"2501.06651","n_code_links":1,"syntology":null},{"paper":"/paper/hyperspectral-imaging-based-perception-in","title":"Hyperspectral Imaging-Based Perception in Autonomous Driving Scenarios: Benchmarking Baseline Semantic Segmentation Models","date":"2024-10-29","arxiv_id":"2410.22101","n_code_links":1,"syntology":null},{"paper":"/paper/a-surprisingly-simple-approach-to-generalized","title":"A Surprisingly Simple Approach to Generalized Few-Shot Semantic Segmentation","date":"2024-09-26","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"title":"A Comparative Analysis of CNN-based Deep Learning Models for Landslide Detection","date":"2024-08-03","arxiv_id":"2408.01692","n_code_links":0,"syntology":null},{"paper":"/paper/make-a-strong-teacher-with-label-assistance-a","title":"Make a Strong Teacher with Label Assistance: A Novel Knowledge Distillation Approach for Semantic Segmentation","date":"2024-07-18","arxiv_id":"2407.13254","n_code_links":1,"syntology":null},{"paper":null,"title":"Evaluation of Deep Learning Semantic Segmentation for Land Cover Mapping on Multispectral, Hyperspectral and High Spatial Aerial Imagery","date":"2024-06-20","arxiv_id":"2406.14220","n_code_links":0,"syntology":null},{"paper":null,"title":"Fuzzy Rank-based Late Fusion Technique for Cytology image Segmentation","date":"2024-03-16","arxiv_id":"2403.10884","n_code_links":0,"syntology":null},{"paper":"/paper/generative-denoise-distillation-simple","title":"Generative Denoise Distillation: Simple Stochastic Noises Induce Efficient Knowledge Transfer for Dense Prediction","date":"2024-01-16","arxiv_id":"2401.08332","n_code_links":1,"syntology":null},{"paper":null,"title":"A knowledge-based data-driven (KBDD) framework for all-day identification of cloud types using satellite remote sensing","date":"2023-12-01","arxiv_id":"2312.00308","n_code_links":0,"syntology":null},{"paper":null,"title":"Equirectangular image construction method for standard CNNs for Semantic Segmentation","date":"2023-10-13","arxiv_id":"2310.09122","n_code_links":0,"syntology":null},{"paper":null,"title":"Evaluation Kidney Layer Segmentation on Whole Slide Imaging using Convolutional Neural Networks and Transformers","date":"2023-09-05","arxiv_id":"2309.02563","n_code_links":0,"syntology":null},{"paper":"/paper/image-segmentation-keras-implementation-of","title":"Image Segmentation Keras : Implementation of Segnet, FCN, UNet, PSPNet and other models in Keras","date":"2023-07-25","arxiv_id":"2307.13215","n_code_links":2,"syntology":null},{"paper":"/paper/sssegmenation-an-open-source-supervised","title":"SSSegmenation: An Open Source Supervised Semantic Segmentation Toolbox Based on PyTorch","date":"2023-05-26","arxiv_id":"2305.17091","n_code_links":1,"syntology":null},{"paper":null,"title":"A Simple and Generic Framework for Feature Distillation via Channel-wise Transformation","date":"2023-03-23","arxiv_id":"2303.13212","n_code_links":0,"syntology":null},{"paper":null,"title":"An End-to-End Two-Phase Deep Learning-Based workflow to Segment Man-made Objects Around Reservoirs","date":"2023-02-07","arxiv_id":"2302.03282","n_code_links":0,"syntology":null},{"paper":null,"title":"Efficient and Effective Methods for Mixed Precision Neural Network Quantization for Faster, Energy-efficient Inference","date":"2023-01-30","arxiv_id":"2301.13330","n_code_links":0,"syntology":null},{"paper":"/paper/a-strong-baseline-for-generalized-few-shot","title":"A Strong Baseline for Generalized Few-Shot Semantic Segmentation","date":"2022-11-25","arxiv_id":"2211.14126","n_code_links":2,"syntology":null},{"paper":null,"title":"Road Rutting Detection using Deep Learning on Images","date":"2022-09-28","arxiv_id":"2209.14225","n_code_links":0,"syntology":null},{"paper":"/paper/massmind-massachusetts-maritime-infrared","title":"MassMIND: Massachusetts Maritime INfrared Dataset","date":"2022-09-09","arxiv_id":"2209.04097","n_code_links":1,"syntology":null},{"paper":null,"title":"Landslide4Sense: Reference Benchmark Data and Deep Learning Models for Landslide Detection","date":"2022-06-01","arxiv_id":"2206.00515","n_code_links":0,"syntology":null},{"paper":"/paper/learning-what-not-to-segment-a-new","title":"Learning What Not to Segment: A New Perspective on Few-Shot Segmentation","date":"2022-03-15","arxiv_id":"2203.07615","n_code_links":1,"syntology":{"ran":14,"of":17,"unverified":3,"pointer_only":0}},{"paper":null,"title":"Boosting Mask R-CNN Performance for Long, Thin Forensic Traces with Pre-Segmentation and IoU Region Merging","date":"2022-03-08","arxiv_id":"2203.03886","n_code_links":0,"syntology":null},{"paper":null,"title":"MSP : Refine Boundary Segmentation via Multiscale Superpixel","date":"2021-12-03","arxiv_id":"2112.01746","n_code_links":0,"syntology":null},{"paper":"/paper/utilizing-attention-linked-blocks-and-pyramid","title":"Utilizing Attention, Linked Blocks, And Pyramid Pooling To Propel Brain Tumor Segmentation In 3D","date":"2021-09-29","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/mining-contextual-information-beyond-image","title":"Mining Contextual Information Beyond Image for Semantic Segmentation","date":"2021-08-26","arxiv_id":"2108.11819","n_code_links":1,"syntology":{"ran":0,"of":2,"unverified":2,"pointer_only":0}},{"paper":null,"title":"Woodscape Fisheye Semantic Segmentation for Autonomous Driving -- CVPR 2021 OmniCV Workshop Challenge","date":"2021-07-17","arxiv_id":"2107.08246","n_code_links":0,"syntology":null},{"paper":"/paper/encoder-decoder-architectures-for-clinically","title":"Encoder-Decoder Architectures for Clinically Relevant Coronary Artery Segmentation","date":"2021-06-21","arxiv_id":"2106.11447","n_code_links":1,"syntology":null},{"paper":"/paper/green-view-index-analysis-and-optimal-green","title":"Analyzing Green View Index and Green View Index best path using Google Street View and deep learning","date":"2021-04-26","arxiv_id":"2104.12627","n_code_links":1,"syntology":null}],"papers_shown":30,"tasks":[{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":41},{"task":"/task/segmentation","name":"Segmentation","papers":26},{"task":"/task/image-segmentation","name":"Image Segmentation","papers":8},{"task":"/task/autonomous-driving","name":"Autonomous Driving","papers":7},{"task":"/task/scene-parsing","name":"Scene Parsing","papers":6},{"task":"/task/image-classification","name":"Image Classification","papers":5},{"task":"/task/scene-understanding","name":"Scene Understanding","papers":5},{"task":"/task/decoder","name":"Decoder","papers":4},{"task":"/task/instance-segmentation","name":"Instance Segmentation","papers":4},{"task":"/task/image-classification","name":"image-classification","papers":4},{"task":"/task/deep-learning","name":"Deep Learning","papers":3},{"task":"/task/few-shot-image-segmentation","name":"Few-Shot Semantic Segmentation","papers":3},{"task":"/task/knowledge-distillation","name":"Knowledge Distillation","papers":3},{"task":"/task/object-detection","name":"Object Detection","papers":3},{"task":"/task/object-detection-1","name":"object-detection","papers":3},{"task":"/task/classification","name":"General Classification","papers":2},{"task":"/task/generalized-few-shot-semantic-segmentation","name":"Generalized Few-Shot Semantic Segmentation","papers":2},{"task":"/task/lesion-segmentation","name":"Lesion Segmentation","papers":2},{"task":"/task/object","name":"Object","papers":2},{"task":"/task/real-time-semantic-segmentation","name":"Real-Time Semantic Segmentation","papers":2}],"tasks_shown":20,"n_tasks":54,"usage_by_year":[{"year":"2016","papers":1},{"year":"2018","papers":5},{"year":"2019","papers":2},{"year":"2020","papers":6},{"year":"2021","papers":9},{"year":"2022","papers":6},{"year":"2023","papers":8},{"year":"2024","papers":7},{"year":"2025","papers":3}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/pspnet"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}