mlsanityData to 7 Oct 2026

Vision Transformers on the Edge: A Comprehensive Survey of Model Compression and Acceleration Strategies

arXiv 2503.02891 ↗First posted 26 Feb 2025cs.CV cs.ARcited by 24

Not on the map. Why?

Abstract (arXiv)

In recent years, vision transformers (ViTs) have emerged as powerful and promising techniques for computer vision tasks such as image classification, object detection, and segmentation. Unlike convolutional neural networks (CNNs), which rely on hierarchical feature extraction, ViTs treat images as sequences of patches and leverage self-attention mechanisms. However, their high computational complexity and memory demands pose significant challenges for deployment on resource-constrained edge devices. To address these limitations, extensive research has focused on model compression techniques and hardware-aware acceleration strategies. Nonetheless, a comprehensive review that systematically categorizes these techniques and their trade-offs in accuracy, efficiency, and hardware adaptability for edge deployment remains lacking. This survey bridges this gap by providing a structured analysis of model compression techniques, software tools for inference on edge, and hardware acceleration strategies for ViTs. We discuss their impact on accuracy, efficiency, and hardware adaptability, highlighting key challenges and emerging research directions to advance ViT deployment on edge platforms, including graphics processing units (GPUs), application-specific integrated circuit (ASICs), and field-programmable gate arrays (FPGAs). The goal is to inspire further research with a contemporary guide on optimizing ViTs for efficient deployment on edge devices.

Key facts. Cited by 24 papers in the map (data through 7 Oct 2026). Builds on 58 of its 112 references that are in the map. First posted on arXiv 26 Feb 2025.

Builds on

58 of 112 references.

References · 58

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2020End-to-End Object Detection with Transformerscited by 7,384
  4. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  5. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 1,998
  6. 2020Knowledge Distillation: A Surveycited by 1,578
  7. 2022SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Modelscited by 1,338
  8. 2023AWQ: Activation-aware Weight Quantization for LLM Compression and Accelerationcited by 1,234
  9. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,213
  10. 2016Semantic Understanding of Scenes through the ADE20K Datasetcited by 1,063
  11. 2016COCO-Stuff: Thing and Stuff Classes in Contextcited by 858
  12. 2022Swin UNETR: Swin Transformers for Semantic Segmentation of Brain Tumors in MRI Imagescited by 823
38 more
  1. 2023Scaling Vision Transformers to 22 Billion Parameterscited by 690
  2. 2018ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardwarecited by 666
  3. 2019Learned Step Size Quantizationcited by 604
  4. 2020Up or Down? Adaptive Rounding for Post-Training Quantizationcited by 600
  5. 2021Post-Training Quantization for Vision Transformercited by 274
  6. 2021Pruning and Quantization for Deep Neural Network Acceleration: A Surveycited by 259
  7. 2021I-BERT: Integer-only BERT Quantizationcited by 250
  8. 2022TinyViT: Fast Pretraining Distillation for Small Vision Transformerscited by 232
  9. 2019Low-bit Quantization of Neural Networks for Efficient Inferencecited by 185
  10. 2021Chasing Sparsity in Vision Transformers: An End-to-End Explorationcited by 181
  11. 2021PTQ4ViT: Post-training quantization for vision transformers with twin uniform quantizationcited by 173
  12. 2021SPViT: Enabling Faster Vision Transformers via Soft Token Pruningcited by 165
  13. 2021FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformercited by 148
  14. 2022LViT: Language meets Vision Transformer in Medical Image Segmentationcited by 110
  15. 2022Q-ViT: Accurate and Fully Quantized Low-bit Vision Transformercited by 106
  16. 2022M3ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-designcited by 97
  17. 2021TransMed: Transformers Advance Multi-modal Medical Image Classificationcited by 85
  18. 2022Unified Visual Transformer Compressioncited by 79
  19. 2020Post-Training Piecewise Linear Quantization for Deep Neural Networkscited by 77
  20. 2023Towards Accurate Post-Training Quantization for Vision Transformercited by 70
  21. 2021Learning Efficient Vision Transformers via Fine-Grained Manifold Distillationcited by 60
  22. 2018FINN-R: An End-to-End Deep-Learning Framework for Fast Exploration of Quantized Neural Networkscited by 54
  23. 2021Softermax: Hardware/Software Co-Design of an Efficient Softmax for Transformerscited by 52
  24. 2022HeatViT: Hardware-Efficient Adaptive Token Pruning for Vision Transformerscited by 46
  25. 2022PSAQ-ViT V2: Towards Accurate and General Data-Free Quantization for Vision Transformerscited by 42
  26. 2022ViTCoD: Vision Transformer Acceleration via Dedicated Algorithm and Accelerator Co-Designcited by 41
  27. 2023A survey on efficient vision transformers: algorithms, techniques, and performance benchmarkingcited by 41
  28. 2022Auto-ViT-Acc: An FPGA-Aware Automatic Acceleration Framework for Vision Transformer with Mixed-Scheme Quantizationcited by 28
  29. 2024AdaLog: Post-Training Quantization for Vision Transformers with Adaptive Logarithm Quantizercited by 28
  30. 2023PIT: Optimization of Dynamic Sparse Deep Learning Models via Permutation Invariant Transformationcited by 25
  31. 2023Categories of Response-Based, Feature-Based, and Relation-Based Knowledge Distillationcited by 19
  32. 2023SwiftTron: An Efficient Hardware Accelerator for Quantized Transformerscited by 17
  33. 2024CLAMP-ViT: Contrastive Data-Free Learning for Adaptive Post-Training Quantization of ViTscited by 17
  34. 2018L1-Norm Batch Normalization for Efficient Training of Deep Neural Networkscited by 15
  35. 2024LPViT: Low-Power Semi-structured Pruning for Vision Transformerscited by 15
  36. 2021HAO: Hardware-aware neural Architecture Optimization for Efficient Inferencecited by 14
  37. 2021Dynamically pruning segformer for efficient semantic segmentationcited by 13
  38. 2023ViTA: A Vision Transformer Inference Accelerator for Edge Applicationscited by 11

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 10; 2026: 14.

24 papers.

Sort:

By area:

  1. 2025ThinkingViT: Matryoshka Thinking Vision Transformer for Elastic Inferencecited by 6
  2. 2025EdgeWisePersona: A Dataset for On-Device User Profiling from Natural Language Interactionscited by 2
  3. 2025FPGA-Enabled Machine Learning Applications in Earth Observation: A Systematic Reviewcited by 2
  4. 2025RCPU: Rotation-Constrained Error Compensation for Structured Pruning of Large Language Modelscited by 2
  5. 2026Vision-Language Model for Accurate Crater Detectioncited by 2
  6. 2025EfficientQuant: An Efficient Post-Training Quantization for CNN-Transformer Hybrid Models on Edge Devicescited by 1
  7. 2025I-Segmenter: Integer-Only Vision Transformer for Efficient Semantic Segmentationcited by 1
  8. 2025Evaluating Deep Learning Models for African Wildlife Image Classification: From DenseNet to Vision Transformerscited by 0
  9. 2025Region-Aware Deformable Convolutionscited by 0
  10. 2025Animal Re-Identification on Microcontrollerscited by 0
  11. 2025Do We Need Reformer for Vision? An Experimental Comparison with Vision Transformerscited by 0
  12. 2026Lightweight Transformer Architectures for Edge Devices in Real-Time Applicationscited by 0
12 more
  1. 2026DSFlash: Comprehensive Panoptic Scene Graph Generation in Realtimecited by 0
  2. 2026HAViT: Historical Attention Vision Transformercited by 0
  3. 2026Video Patch Pruning: Efficient Video Instance Segmentation via Early Token Reductioncited by 0
  4. 2026HST-HGN: Heterogeneous Spatial-Temporal Hypergraph Networks with Bidirectional State Space Models for Global Fatigue Assessmentcited by 0
  5. 2026Joint Architecture-Token-Bitwidth Multi-Axis Optimization of Vision Transformers for Semiconductor IC Packagingcited by 0
  6. 2026HydraCIL: Decoupled Class-Incremental Learning through Prototype-Guided Multi-Head Classifierscited by 0
  7. 2026Edge Physical AI Deployment of Vision Transformers on Heterogeneous Edge GPU Targeting Autonomous Vehiclescited by 0
  8. 2026Recursive transformers for semiconductor thermo-mechanical reliabilitycited by 0
  9. 2026MixFrag: Fragility-Guided Mixed-Precision Post-Training Quantization for Vision Transformerscited by 0
  10. 2026Recent Developments in Transformer Inference Deployment on FPGA Platforms: A Surveycited by 0
  11. 2026Real-World Perception for Autonomous Driving in Adverse Weather: Enhancing Standard Detectors via Foundation-Guided Auto-Annotationcited by 0
  12. 2026Momentum-Guided Federated Split Distillation for Personalized Temporal Edge Intelligencecited by 0