mlsanityData to 7 Oct 2026

Dynamically pruning segformer for efficient semantic segmentation

arXiv 2111.09499 ↗First posted 18 Nov 2021cs.CV cs.LGcited by 13

Not on the map. Why?

Abstract (arXiv)

As one of the successful Transformer-based models in computer vision tasks, SegFormer demonstrates superior performance in semantic segmentation. Nevertheless, the high computational cost greatly challenges the deployment of SegFormer on edge devices. In this paper, we seek to design a lightweight SegFormer for efficient semantic segmentation. Based on the observation that neurons in SegFormer layers exhibit large variances across different images, we propose a dynamic gated linear layer, which prunes the most uninformative set of neurons based on the input instance. To improve the dynamically pruned SegFormer, we also introduce two-stage knowledge distillation to transfer the knowledge within the original teacher to the pruned student network. Experimental results show that our method can significantly reduce the computation overhead of SegFormer without an apparent performance drop. For instance, we can achieve 36.9% mIoU with only 3.3G FLOPs on ADE20K, saving more than 60% computation with the drop of only 0.5% in mIoU

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 21 of its 23 references that are in the map. First posted on arXiv 18 Nov 2021.

Builds on

21 of 23 references.

References · 21

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  3. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  4. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  5. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  6. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  7. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  8. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,923
  9. 2016Pyramid Scene Parsing Networkcited by 2,472
  10. 2016Identity Mappings in Deep Residual Networkscited by 1,960
  11. 2020Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformerscited by 1,368
  12. 2019TinyBERT: Distilling BERT for Natural Language Understandingcited by 1,153
9 more
  1. 2021Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNetcited by 1,096
  2. 2018CCNet: Criss-Cross Attention for Semantic Segmentationcited by 717
  3. 2017Learning Efficient Convolutional Networks through Network Slimmingcited by 673
  4. 2019Segmentation Transformer: Object-Contextual Representations for Semantic Segmentationcited by 573
  5. 2018Context Encoding for Semantic Segmentationcited by 289
  6. 2017ICNet for Real-Time Semantic Segmentation on High-Resolution Imagescited by 261
  7. 2020BinaryBERT: Pushing the Limit of BERT Quantizationcited by 175
  8. 2020How Much Position Information Do Convolutional Neural Networks Encode?cited by 171
  9. 2018Dynamic Channel Pruning: Feature Boosting and Suppressioncited by 129

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 1; 2024: 3; 2025: 6; 2026: 1.

13 papers.

Sort:

By area:

  1. 2025Vision Transformers on the Edge: A Comprehensive Survey of Model Compression and Acceleration Strategiescited by 24
  2. 2022TransKD: Transformer Knowledge Distillation for Efficient Semantic Segmentationcited by 17
  3. 2024HyperspectralViTs: General Hyperspectral Models for On-board Remote Sensingcited by 11
  4. 2024Segformer++: Efficient Token-Merging Strategies for High-Resolution Semantic Segmentationcited by 9
  5. 2023WHC: Weighted Hybrid Criterion for Filter Pruning on Convolutional Neural Networkscited by 6
  6. 2022Class Based Thresholding in Early Exit Semantic Segmentation Networkscited by 5
  7. 2025DUDA: Distilled Unsupervised Domain Adaptation for Lightweight Semantic Segmentationcited by 3
  8. 2024Comb, Prune, Distill: Towards Unified Pruning for Vision Model Compressioncited by 1
  9. 2025Optimization of DNN-based HSI Segmentation FPGA-based SoC for ADS: A Practical Approachcited by 1
  10. 2025TSLA: A Task-Specific Learning Adaptation for Semantic Segmentation on Autonomous Vehicles Platformcited by 1
  11. 2025Enabling Plant Phenotyping in Weedy Environments using Multi-Modal Imagery via Synthetic and Generated Training Datacited by 0
  12. 2025ArmFormer: Lightweight Transformer Architecture for Real-Time Multi-Class Weapon Segmentation and Classificationcited by 0
1 more
  1. 2026StaticSegFormer: An Efficient High-Performance Semantic Segmentation Based on Static Structured Pruningcited by 0