mlsanityData to 14 Oct 2026

EfficientQuant: An Efficient Post-Training Quantization for CNN-Transformer Hybrid Models on Edge Devices

arXiv 2506.11093 ↗First posted 5 Jun 2025cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

Hybrid models that combine convolutional and transformer blocks offer strong performance in computer vision (CV) tasks but are resource-intensive for edge deployment. Although post-training quantization (PTQ) can help reduce resource demand, its application to hybrid models remains limited. We propose EfficientQuant, a novel structure-aware PTQ approach that applies uniform quantization to convolutional blocks and log2 quantization to transformer blocks. EfficientQuant achieves 2.5 × - 8.7 × latency reduction with minimal accuracy loss on the ImageNet-1K dataset. It further demonstrates low latency and memory efficiency on edge devices, making it practical for real-world deployment.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 24 of its 30 references that are in the map. First posted on arXiv 5 Jun 2025.

Builds on

24 of 30 references.

References · 24

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,593
  3. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,218
  4. 2021UNETR: Transformers for 3D Medical Image Segmentationcited by 959
  5. 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 815
  6. 2019Once-for-All: Train One Network and Specialize it for Efficient Deploymentcited by 787
  7. 2021MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformercited by 642
  8. 2018PACT: Parameterized Clipping Activation for Quantized Neural Networkscited by 467
  9. 2021Intriguing Properties of Vision Transformerscited by 446
  10. 2022EfficientFormer: Vision Transformers at MobileNet Speedcited by 241
  11. 2019Low-bit Quantization of Neural Networks for Efficient Inferencecited by 193
  12. 2021PTQ4ViT: Post-training quantization for vision transformers with twin uniform quantizationcited by 179
12 more
  1. 2022Separable Self-attention for Mobile Vision Transformerscited by 163
  2. 2018Learning to Quantize Deep Networks by Optimizing Quantization Intervals with Task Losscited by 160
  3. 2019Improving Neural Network Quantization without Retraining using Outlier Channel Splittingcited by 151
  4. 2022RepQ-ViT: Scale Reparameterization for Post-Training Quantization of Vision Transformerscited by 137
  5. 2022EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applicationscited by 121
  6. 2022Rethinking Vision Transformers for MobileNet Size and Speedcited by 121
  7. 2020EasyQuant: Post-training Quantization via Scale Optimizationcited by 57
  8. 2024AdaLog: Post-Training Quantization for Vision Transformers with Adaptive Logarithm Quantizercited by 29
  9. 2025Vision Transformers on the Edge: A Comprehensive Survey of Model Compression and Acceleration Strategiescited by 24
  10. 2018Quantization for Rapid Deployment of Deep Neural Networkscited by 20
  11. 2021HPTQ: Hardware-Friendly Post Training Quantizationcited by 10
  12. 2023Q-HyViT: Post-Training Quantization of Hybrid Vision Transformers with Bridge Block Reconstruction for IoT Systemscited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Same Predictions, Different Reasons: The Effect of Quantization on Model Explanationscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2021FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformer
  2. 2023TSPTQ-ViT: Two-scaled post-training quantization for vision transformer
  3. 2024MPTQ-ViT: Mixed-Precision Post-Training Quantization for Vision Transformer
  4. 2024DopQ-ViT: Towards Distribution-Friendly and Outlier-Aware Post-Training Quantization for Vision Transformers
  5. 2022NoisyQuant: Noisy Bias-Enhanced Post-Training Activation Quantization for Vision Transformers
  6. 2024FrameQuant: Flexible Low-Bit Quantization for Transformers
  7. 2024M2-ViT: Accelerating Hybrid Vision Transformers with Two-Level Mixed Quantization
  8. 2024ADFQ-ViT: Activation-Distribution-Friendly Post-Training Quantization for Vision Transformers