Methods › Computer Vision › Semantic Segmentation Models › SegFormer
SegFormer
Introduced by Enze Xie et al. in SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
SegFormer is a Transformer-based framework for semantic segmentation that unifies Transformers with lightweight multilayer perceptron (MLP) decoders. SegFormer has two appealing features: 1) SegFormer comprises a novel hierarchically structured Transformer encoder which outputs multiscale features. It does not need positional encoding, thereby avoiding the interpolation of positional codes which leads to decreased performance when the testing resolution differs from training. 2) SegFormer avoids complex decoders. The proposed MLP decoder aggregates information from different layers, and thus combining both local attention and global attention to render powerful representations.
In Syntology repository known, no verified implementation (declared_code; repositories: 5 listed of 26 in the graph, strongest link: official). This answer is about arXiv:2105.15203, the paper the archive credits with this method.
Origin paper of this answer, arXiv:2105.15203 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 66 ran (of which 22 constructed an object rather than computing a result; 52 with no instrument failure: 1 honoured, 2 violated, 49 with no contract checked; 14 where Syntology's instrument failed) · 20 unverified (of 86 harvested samples) · 20 pointer-only (licence). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.
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: 23 · where Syntology ran a sample: 4 (4 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 (4 of 47 tagged: 4 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.
-
From Pixels to Damage Severity: Estimating Earthquake Impacts Using Semantic Segmentation of Social Media Images 3 Jul 2025 · 0 repositories · arXiv:2507.02781
-
Leveraging Modified Ex Situ Tomography Data for Segmentation of In Situ Synchrotron X-Ray Computed Tomography 27 Apr 2025 · 0 repositories · arXiv:2504.19200
-
SAR Object Detection with Self-Supervised Pretraining and Curriculum-Aware Sampling 17 Apr 2025 · 0 repositories · arXiv:2504.13310
-
Improving underwater semantic segmentation with underwater image quality attention and muti-scale aggregation attention 30 Mar 2025 · 1 repository · arXiv:2503.23422
-
Comprehensive Evaluation of OCT-based Automated Segmentation of Retinal Layer, Fluid and Hyper-Reflective Foci: Impact on Diabetic Retinopathy Severity Assessment 3 Mar 2025 · 0 repositories · arXiv:2503.01248
-
Cross-Model Transferability of Adversarial Patches in Real-time Segmentation for Autonomous Driving 22 Feb 2025 · 1 repository · arXiv:2502.16012
-
Global Average Feature Augmentation for Robust Semantic Segmentation with Transformers 2 Dec 2024 · 0 repositories · arXiv:2412.01941
-
SynDiff-AD: Improving Semantic Segmentation and End-to-End Autonomous Driving with Synthetic Data from Latent Diffusion Models 25 Nov 2024 · 0 repositories · arXiv:2411.16776
-
Habaek: High-performance water segmentation through dataset expansion and inductive bias optimization 21 Oct 2024 · 1 repository · arXiv:2410.15794
-
Risk Assessment for Autonomous Landing in Urban Environments using Semantic Segmentation 16 Oct 2024 · 0 repositories · arXiv:2410.12988
-
Adapting Segment Anything Model to Melanoma Segmentation in Microscopy Slide Images 3 Oct 2024 · 0 repositories · arXiv:2410.02207
-
Semantic Segmentation of Unmanned Aerial Vehicle Remote Sensing Images using SegFormer 1 Oct 2024 · 0 repositories · arXiv:2410.01092
-
AMBER -- Advanced SegFormer for Multi-Band Image Segmentation: an application to Hyperspectral Imaging 14 Sep 2024 · 0 repositories · arXiv:2409.09386
-
SHARP-Net: A Refined Pyramid Network for Deficiency Segmentation in Culverts and Sewer Pipes 2 Aug 2024 · 0 repositories · arXiv:2408.08879
-
MagicBathyNet: A Multimodal Remote Sensing Dataset for Bathymetry Prediction and Pixel-based Classification in Shallow Waters 24 May 2024 · 1 repository · arXiv:2405.15477
-
Segformer++: Efficient Token-Merging Strategies for High-Resolution Semantic Segmentation 23 May 2024 · 2 repositories · arXiv:2405.14467
-
wmh_seg: Transformer based U-Net for Robust and Automatic White Matter Hyperintensity Segmentation across 1.5T, 3T and 7T 20 Feb 2024 · 1 repository · arXiv:2402.12701
-
Kitchen Food Waste Image Segmentation and Classification for Compost Nutrients Estimation 26 Jan 2024 · 0 repositories · arXiv:2401.15175
-
CaBuAr: California Burned Areas dataset for delineation 21 Jan 2024 · 1 repository · arXiv:2401.11519
-
U-MixFormer: UNet-like Transformer with Mix-Attention for Efficient Semantic Segmentation 11 Dec 2023 · 1 repository · arXiv:2312.06272
-
Enhancing Transformer-Based Segmentation for Breast Cancer Diagnosis using Auto-Augmentation and Search Optimisation Techniques 18 Nov 2023 · 0 repositories · arXiv:2311.11065
-
Depth-guided Free-space Segmentation for a Mobile Robot 3 Nov 2023 · 0 repositories · arXiv:2311.01966
-
MineSegSAT: An automated system to evaluate mining disturbed area extents from Sentinel-2 imagery 3 Nov 2023 · 1 repository · arXiv:2311.01676
-
Robust Burned Area Delineation through Multitask Learning 15 Sep 2023 · 2 repositories · arXiv:2309.08368
-
dacl10k: Benchmark for Semantic Bridge Damage Segmentation 1 Sep 2023 · 1 repository · arXiv:2309.00460
-
FoSp: Focus and Separation Network for Early Smoke Segmentation 7 Jun 2023 · 1 repository · arXiv:2306.04474
-
SAM for Poultry Science 17 May 2023 · 0 repositories · arXiv:2305.10254
-
Concurrent Misclassification and Out-of-Distribution Detection for Semantic Segmentation via Energy-Based Normalizing Flow 16 May 2023 · 1 repository · arXiv:2305.09610
-
Radious: Unveiling the Enigma of Dental Radiology with BEIT Adaptor and Mask2Former in Semantic Segmentation 10 May 2023 · 0 repositories · arXiv:2305.06236
-
Do Vision and Language Models Share Concepts? A Vector Space Alignment Study 13 Feb 2023 · 1 repository · arXiv:2302.06555Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples)
-
BuildSeg: A General Framework for the Segmentation of Buildings 15 Jan 2023 · 0 repositories · arXiv:2301.06190
-
Head-Free Lightweight Semantic Segmentation with Linear Transformer 11 Jan 2023 · 1 repository · arXiv:2301.04648
-
EfficientViT: Lightweight Multi-Scale Attention for High-Resolution Dense Prediction 1 Jan 2023 · 1 repository
-
Semi-Supervised Semantic Segmentation Methods for UW-OCTA Diabetic Retinopathy Grade Assessment 27 Dec 2022 · 0 repositories · arXiv:2212.13486
-
Vision Transformer Computation and Resilience for Dynamic Inference 6 Dec 2022 · 0 repositories · arXiv:2212.02687
-
FsaNet: Frequency Self-attention for Semantic Segmentation 28 Nov 2022 · 1 repository · arXiv:2211.15595
-
1st Place Solution of The Robust Vision Challenge 2022 Semantic Segmentation Track 23 Oct 2022 · 1 repository · arXiv:2210.12852
-
The Outcome of the 2022 Landslide4Sense Competition: Advanced Landslide Detection from Multi-Source Satellite Imagery 6 Sep 2022 · 0 repositories · arXiv:2209.02556
-
SiamixFormer: a fully-transformer Siamese network with temporal Fusion for accurate building detection and change detection in bi-temporal remote sensing images 1 Aug 2022 · 0 repositories · arXiv:2208.00657
-
Improving Semantic Segmentation in Transformers using Hierarchical Inter-Level Attention 5 Jul 2022 · 0 repositories · arXiv:2207.02126
-
CV 3315 Is All You Need : Semantic Segmentation Competition 25 Jun 2022 · 1 repository · arXiv:2206.12571
-
EfficientViT: Multi-Scale Linear Attention for High-Resolution Dense Prediction 29 May 2022 · 6 repositories · arXiv:2205.14756Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples)
-
A Transformer-Based Siamese Network for Change Detection 4 Jan 2022 · 3 repositories · arXiv:2201.01293Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified (of 6 harvested samples) · 3 pointer-only (licence)
-
FBNetV5: Neural Architecture Search for Multiple Tasks in One Run 19 Nov 2021 · 0 repositories · arXiv:2111.10007
-
Dynamically pruning segformer for efficient semantic segmentation 18 Nov 2021 · 0 repositories · arXiv:2111.09499
-
Panoptic SegFormer: Delving Deeper into Panoptic Segmentation with Transformers 8 Sep 2021 · 3 repositories · arXiv:2109.03814
-
SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers 31 May 2021 · 28 repositories · arXiv:2105.15203Syntology official: no sample here; runs from other or unrecorded repositories · 66 ran (of which 22 constructed an object rather than computing a result; 52 with no instrument failure: 1 honoured, 2 violated, 49 with no contract checked; 14 where Syntology's instrument failed) · 20 unverified (of 86 harvested samples) · 20 pointer-only (licence)
Tasks archive 2025-07-28
20 shown of 57 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