mlsanityData to 14 Oct 2026

CLAMP-ViT: Contrastive Data-Free Learning for Adaptive Post-Training Quantization of ViTs

arXiv 2407.05266 ↗First posted 7 Jul 2024cs.CV cs.AI eess.IVcited by 17

Not on the map. Why?

Abstract (arXiv)

We present CLAMP-ViT, a data-free post-training quantization method for vision transformers (ViTs). We identify the limitations of recent techniques, notably their inability to leverage meaningful inter-patch relationships, leading to the generation of simplistic and semantically vague data, impacting quantization accuracy. CLAMP-ViT employs a two-stage approach, cyclically adapting between data generation and model quantization. Specifically, we incorporate a patch-level contrastive learning scheme to generate richer, semantically meaningful data. Furthermore, we leverage contrastive learning in layer-wise evolutionary search for fixed- and mixed-precision quantization to identify optimal quantization parameters while mitigating the effects of a non-smooth loss landscape. Extensive evaluations across various vision tasks demonstrate the superiority of CLAMP-ViT, with performance improvements of up to 3% in top-1 accuracy for classification, 0.6 mAP for object detection, and 1.5 mIoU for segmentation at similar or better compression ratio over existing alternatives. Code is available at https://github.com/georgia-tech-synergy-lab/CLAMP-ViT.git

Key facts. Cited by 17 papers in the map (data through 14 Oct 2026). Builds on 38 of its 52 references that are in the map. First posted on arXiv 7 Jul 2024.

Builds on

38 of 52 references.

References · 38

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  4. 2020Training data-efficient image transformers & distillation through attentioncited by 4,586
  5. 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,385
  6. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,276
  7. 2018Unified Perceptual Parsing for Scene Understandingcited by 1,271
  8. 2017Visualizing the Loss Landscape of Neural Netscited by 1,130
  9. 2016Semantic Understanding of Scenes through the ADE20K Datasetcited by 1,069
  10. 2021Segmenter: Transformer for Semantic Segmentationcited by 855
  11. 2019Dreaming to Distill: Data-free Knowledge Transfer via DeepInversioncited by 423
  12. 2021Post-Training Quantization for Vision Transformercited by 278
26 more
  1. 2018LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networkscited by 274
  2. 2020ZeroQ: A Novel Zero Shot Quantization Frameworkcited by 269
  3. 2022EfficientFormer: Vision Transformers at MobileNet Speedcited by 241
  4. 2021PTQ4ViT: Post-training quantization for vision transformers with twin uniform quantizationcited by 179
  5. 2021FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformercited by 151
  6. 2021Decoupled Contrastive Learningcited by 143
  7. 2022RepQ-ViT: Scale Reparameterization for Post-Training Quantization of Vision Transformerscited by 137
  8. 2022Q-ViT: Accurate and Fully Quantized Low-bit Vision Transformercited by 108
  9. 2022I-ViT: Integer-only Quantization for Efficient Vision Transformer Inferencecited by 95
  10. 2023CompletionFormer: Depth Completion with Convolutions and Vision Transformerscited by 93
  11. 2022Patch Similarity Aware Data-Free Quantization for Vision Transformerscited by 56
  12. 2022Robust Contrastive Learning against Noisy Viewscited by 45
  13. 2021IntraQ: Learning Synthetic Images with Intra-Class Heterogeneity for Zero-Shot Network Quantizationcited by 43
  14. 2022PSAQ-ViT V2: Towards Accurate and General Data-Free Quantization for Vision Transformerscited by 42
  15. 2021Qimera: Data-free Quantization with Synthetic Boundary Supporting Samplescited by 40
  16. 2018An Introduction to Image Synthesis with Generative Adversarial Netscited by 32
  17. 2023EMQ: Evolving Training-free Proxies for Automated Mixed Precision Quantizationcited by 22
  18. 2018Probabilistic Binary Neural Networkscited by 21
  19. 2023Jumping through Local Minima: Quantization in the Loss Landscape of Vision Transformerscited by 18
  20. 2022Bootstrap Generalization Ability from Loss Landscape Perspectivecited by 16
  21. 2023Patch-wise Mixed-Precision Quantization of Vision Transformercited by 15
  22. 2021BMPQ: Bit-Gradient Sensitivity Driven Mixed-Precision Quantization of DNNs from Scratchcited by 11
  23. 2022Synergistic Self-supervised and Quantization Learningcited by 10
  24. 2024LRP-QViT: Mixed-Precision Vision Transformer Quantization via Layer-wise Relevance Propagationcited by 8
  25. 2024Algorithm-Hardware Co-Design of Distribution-Aware Logarithmic-Posit Encodings for Efficient DNN Inferencecited by 7
  26. 2022Positive-Negative Equal Contrastive Loss for Semantic Segmentationcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 4; 2025: 7; 2026: 6.

17 papers.

Sort:

By area:

  1. 2024MicroScopiQ: Accelerating Foundational Models through Outlier-Aware Microscaling Quantizationcited by 28
  2. 2025Vision Transformers on the Edge: A Comprehensive Survey of Model Compression and Acceleration Strategiescited by 24
  3. 2024QT-DoG: Quantization-aware Training for Domain Generalizationcited by 13
  4. 2025Low-bit Model Quantization for Deep Neural Networks: A Surveycited by 11
  5. 2024MimiQ: Low-Bit Data-Free Quantization of Vision Transformers with Encouraging Inter-Head Attention Similaritycited by 9
  6. 2025Zero-shot Quantization: A Comprehensive Surveycited by 8
  7. 2025OuroMamba: A Data-Free Quantization Framework for Vision Mambacited by 5
  8. 2025LVLM-Compress-Bench: Benchmarking the Broader Impact of Large Vision-Language Model Compressioncited by 4
  9. 2024Semantic Alignment and Reinforcement for Data-Free Quantization of Vision Transformerscited by 3
  10. 2025AIRCHITECT v2: Learning the Hardware Accelerator Design Space through Unified Representationscited by 1
  11. 2025IPTQ-ViT: Post-Training Quantization of Non-linear Functions for Integer-only Vision Transformerscited by 1
  12. 2026Joint Post-Training Quantization of Vision Transformers with Learned Prompt-Guided Data Generationcited by 1
5 more
  1. 2026SynQ: Accurate Zero-shot Quantization by Synthesis-aware Fine-tuningcited by 1
  2. 2026Selective Coupling of Decoupled Informative Regions: Masked Attention Alignment for Data-Free Quantization of Vision Transformerscited by 1
  3. 2026QFlash: Bridging Quantization and Memory Efficiency in Vision Transformer Attentioncited by 0
  4. 2026UniDFKD: A Unified Semantic Prior Framework for Architecture-Agnostic Data-Free Knowledge Distillationcited by 0
  5. 2026IDeaL: Data-Free Multi-Teacher Distillation via Improved Dead Leavescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2022CPT-V: A Contrastive Approach to Post-Training Quantization of Vision Transformers
  2. 2024DopQ-ViT: Towards Distribution-Friendly and Outlier-Aware Post-Training Quantization for Vision Transformers
  3. 2023I&S-ViT: An Inclusive & Stable Method for Pushing the Limit of Post-Training ViTs Quantization
  4. 2024MPTQ-ViT: Mixed-Precision Post-Training Quantization for Vision Transformer
  5. 2024ADFQ-ViT: Activation-Distribution-Friendly Post-Training Quantization for Vision Transformers
  6. 2025AIQViT: Architecture-Informed Post-Training Quantization for Vision Transformers
  7. 2025DFQ-ViT: Data-Free Quantization for Vision Transformers without Fine-tuning
  8. 2024AdaLog: Post-Training Quantization for Vision Transformers with Adaptive Logarithm Quantizer