mlsanityData to 7 Oct 2026

EasyQuant: Post-training Quantization via Scale Optimization

arXiv 2006.16669 ↗First posted 30 Jun 2020cs.CV cs.LG eess.IVcited by 57

Not on the map. Why?

Abstract (arXiv)

The 8 bits quantization has been widely applied to accelerate network inference in various deep learning applications. There are two kinds of quantization methods, training-based quantization and post-training quantization. Training-based approach suffers from a cumbersome training process, while post-training quantization may lead to unacceptable accuracy drop. In this paper, we present an efficient and simple post-training method via scale optimization, named EasyQuant (EQ),that could obtain comparable accuracy with the training-based method.Specifically, we first alternately optimize scales of weights and activations for all layers target at convolutional outputs to further obtain the high quantization precision. Then, we lower down bit width to INT7 both for weights and activations, and adopt INT16 intermediate storage and integer Winograd convolution implementation to accelerate inference.Experimental results on various computer vision tasks show that EQ outperforms the TensorRT method and can achieve near INT8 accuracy in 7 bits width post-training.

Key facts. Cited by 57 papers in the map (data through 7 Oct 2026). First posted on arXiv 30 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 8; 2023: 17; 2024: 15; 2025: 8; 2026: 5.

57 papers.

Sort:

By area:

  1. 2021Post-Training Quantization for Vision Transformercited by 274
  2. 2023Q-Diffusion: Quantizing Diffusion Modelscited by 266
  3. 2022Post-training Quantization on Diffusion Modelscited by 262
  4. 2022Outlier Suppression: Pushing the Limit of Low-bit Transformer Language Modelscited by 176
  5. 2021PTQ4ViT: Post-training quantization for vision transformers with twin uniform quantizationcited by 173
  6. 2022PD-Quant: Post-Training Quantization based on Prediction Difference Metriccited by 73
  7. 2023Towards Accurate Post-Training Quantization for Vision Transformercited by 70
  8. 2023LLM-FP4: 4-Bit Floating-Point Quantized Transformerscited by 65
  9. 2023QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Modelscited by 63
  10. 2022NoisyQuant: Noisy Bias-Enhanced Post-Training Activation Quantization for Vision Transformerscited by 59
  11. 2022Patch Similarity Aware Data-Free Quantization for Vision Transformerscited by 55
  12. 2022PSAQ-ViT V2: Towards Accurate and General Data-Free Quantization for Vision Transformerscited by 42
38 more
  1. 2023CBQ: Cross-Block Quantization for Large Language Modelscited by 34
  2. 2023TinySAM: Pushing the Envelope for Efficient Segment Anything Modelcited by 33
  3. 2024LiDAR-PTQ: Post-Training Quantization for Point Cloud 3D Object Detectioncited by 29
  4. 2024AdaLog: Post-Training Quantization for Vision Transformers with Adaptive Logarithm Quantizercited by 28
  5. 2024Towards Accurate Post-Training Quantization of Vision Transformers via Error Reductioncited by 23
  6. 2023I&S-ViT: An Inclusive & Stable Method for Pushing the Limit of Post-Training ViTs Quantizationcited by 19
  7. 2023Communication-Efficient Split Learning via Adaptive Feature-Wise Compressioncited by 18
  8. 2023Jumping through Local Minima: Quantization in the Loss Landscape of Vision Transformerscited by 18
  9. 2023Efficient Quantization Strategies for Latent Diffusion Modelscited by 16
  10. 2024Model Quantization and Hardware Acceleration for Vision Transformers: A Comprehensive Surveycited by 13
  11. 2025QuantV2X: A Fully Quantized Multi-Agent System for Cooperative Perceptioncited by 11
  12. 2025QUARK: Quantization-Enabled Circuit Sharing for Transformer Acceleration by Exploiting Common Patterns in Nonlinear Operationscited by 10
  13. 2023Benchmarking the Reliability of Post-training Quantization: a Particular Focus on Worst-case Performancecited by 8
  14. 2024Memory-Efficient Fine-Tuning for Quantized Diffusion Modelcited by 8
  15. 2023A Model for Every User and Budget: Label-Free and Personalized Mixed-Precision Quantizationcited by 7
  16. 2024Lossless KV Cache Compression to 2%cited by 7
  17. 2023Q-HyViT: Post-Training Quantization of Hybrid Vision Transformers with Bridge Block Reconstruction for IoT Systemscited by 6
  18. 2023Post-Training Quantization for Re-parameterization via Coarse & Fine Weight Splittingcited by 6
  19. 2022Analysis of Quantization on MLP-based Vision Modelscited by 5
  20. 2023EPTQ: Enhanced Post-Training Quantization via Hessian-guided Network-wise Optimizationcited by 5
  21. 2024Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsitycited by 5
  22. 2025Error Propagation Mechanisms and Compensation Strategies for Quantized Diffusioncited by 5
  23. 2024P2-ViT: Power-of-Two Post-Training Quantization and Acceleration for Fully Quantized Vision Transformercited by 4
  24. 2025Post-Training Quantization for Vision Mamba with k-Scaled Quantization and Reparameterizationcited by 4
  25. 2024Trio-ViT: Post-Training Quantization and Acceleration for Softmax-Free Efficient Vision Transformercited by 3
  26. 2024An Analysis on Quantizing Diffusion Transformerscited by 3
  27. 2025Hardware/Software Co-Design of RISC-V Extensions for Accelerating Sparse DNNs on FPGAscited by 3
  28. 2023ACQ: Improving Generative Data-free Quantization Via Attention Correctioncited by 2
  29. 2023Improving Post-Training Quantization on Object Detection with Task Loss-Guided Lp Metriccited by 2
  30. 2024Differentiable Search for Finding Optimal Quantization Strategycited by 2
  31. 2025Communication Efficient Split Learning of ViTs with Attention-based Double Compressioncited by 2
  32. 2026Saliency-Aware Regularized Quantization Calibration for Large Language Modelscited by 2
  33. 2021PTQ-SL: Exploring the Sub-layerwise Post-training Quantizationcited by 1
  34. 2022CPT-V: A Contrastive Approach to Post-Training Quantization of Vision Transformerscited by 1
  35. 2024Minimize Quantization Output Error with Bias Compensationcited by 1
  36. 2024Selective Focus: Investigating Semantics Sensitivity in Post-training Quantization for Lane Detectioncited by 1
  37. 2025EfficientQuant: An Efficient Post-Training Quantization for CNN-Transformer Hybrid Models on Edge Devicescited by 1
  38. 2021Faster Convolution Inference Through Using Pre-Calculated Lookup Tablescited by 0

50 most cited of 57 All 57 (JSON)