Image de couverture de livre

Stabilizing Quantization-Aware Training by Implicit-Regularization on Hessian Matrix

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Pang, Junbiao, Cai, Tianyang
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

In-Distribution Consistency Regularization Improves the Generalization of Quantization-Aware Training
par: Pang, Junbiao, et autres
Publié: (2024)

MEC-Quant: Maximum Entropy Coding for Extremely Low Bit Quantization-Aware Training
par: Pang, Junbiao, et autres
Publié: (2025)

Efficiently Training A Flat Neural Network Before It has been Quantizated
par: Xia, Peng, et autres
Publié: (2025)

Adaptively Sampling-Reusing-Mixing Decomposed Gradients to Speed Up Sharpness Aware Minimization
par: Deng, Jiaxin, et autres
Publié: (2025)

NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning
par: Xu, Jiayu, et autres
Publié: (2026)

Asymptotic Unbiased Sample Sampling to Speed Up Sharpness-Aware Minimization
par: Deng, Jiaxin, et autres
Publié: (2024)

Fast Measuring Pavement Crack Width by Cascading Principal Component Analysis
par: Wang, Zhicheng, et autres
Publié: (2025)

Bilateral Sharpness-Aware Minimization for Flatter Minima
par: Deng, Jiaxin, et autres
Publié: (2024)

Modeling Multi-Granularity Context Information Flow for Pavement Crack Detection
par: Pang, Junbiao, et autres
Publié: (2024)

Decorrelating Structure via Adapters Makes Ensemble Learning Practical for Semi-supervised Learning
par: Wu, Jiaqi, et autres
Publié: (2024)

APHQ-ViT: Post-Training Quantization with Average Perturbation Hessian Based Reconstruction for Vision Transformers
par: Wu, Zhuguanyu, et autres
Publié: (2025)

Distribution-Aware Hadamard Quantization for Hardware-Efficient Implicit Neural Representations
par: Zhou, Wenyong, et autres
Publié: (2025)

EPTQ: Enhanced Post-Training Quantization via Hessian-guided Network-wise Optimization
par: Gordon, Ofir, et autres
Publié: (2023)

MGVQ: Synergizing Multi-dimensional Sensitivity-Aware and Gradient-Hessian Fusion for Vector Quantization
par: Wang, Zhong, et autres
Publié: (2026)

Scheduling Weight Transitions for Quantization-Aware Training
par: Lee, Junghyup, et autres
Publié: (2024)

Uncertainty-aware Long-tailed Weights Model the Utility of Pseudo-labels for Semi-supervised Learning
par: Wu, Jiaqi, et autres
Publié: (2025)

On Quantizing Implicit Neural Representations
par: Gordon, Cameron, et autres
Publié: (2022)

FraQAT: Quantization Aware Training with Fractional bits
par: Morreale, Luca, et autres
Publié: (2025)

Sensitivity-Aware Post-Training Quantization for Deep Neural Networks
par: Zheng, Zekang, et autres
Publié: (2025)

Outlier-Aware Post-Training Quantization for Image Super-Resolution
par: Wang, Hailing, et autres
Publié: (2025)

Task-Specific Zero-shot Quantization-Aware Training for Object Detection
par: Li, Changhao, et autres
Publié: (2025)

Tail-Aware Post-Training Quantization for 3D Geometry Models
par: Pan, Sicheng, et autres
Publié: (2026)

Effective Gradient Sample Size via Variation Estimation for Accelerating Sharpness aware Minimization
par: Deng, Jiaxin, et autres
Publié: (2024)

A Channel-ensemble Approach: Unbiased and Low-variance Pseudo-labels is Critical for Semi-supervised Classification
par: Wu, Jiaqi, et autres
Publié: (2024)

Technical Report: Activation Residual Hessian Quantization (ARHQ) for Low-Bit LLM Quantization
par: Wang, YiFeng, et autres
Publié: (2026)

QGen: On the Ability to Generalize in Quantization Aware Training
par: AskariHemmat, MohammadHossein, et autres
Publié: (2024)

CR-QAT: Curriculum Relational Quantization-Aware Training for Open-Vocabulary Object Detection
par: Park, Jinyeong, et autres
Publié: (2026)

Directed Ordinal Diffusion Regularization for Progression-Aware Diabetic Retinopathy Grading
par: Chen, Huangwei, et autres
Publié: (2026)

Learning Topology-Aware Implicit Field for Unified Pulmonary Tree Modeling with Incomplete Topological Supervision
par: Weng, Ziqiao, et autres
Publié: (2026)

Pixel-Wise Symbol Spotting via Progressive Points Location for Parsing CAD Images
par: Pang, Junbiao, et autres
Publié: (2024)

HQ-DM: Single Hadamard Transformation-Based Quantization-Aware Training for Low-Bit Diffusion Models
par: Mao, Shizhuo, et autres
Publié: (2025)

DopQ-ViT: Towards Distribution-Friendly and Outlier-Aware Post-Training Quantization for Vision Transformers
par: Yang, Lianwei, et autres
Publié: (2024)

Fine-Grained Post-Training Quantization for Large Vision Language Models with Quantization-Aware Integrated Gradients
par: Xiang, Ziwei, et autres
Publié: (2026)

Sampling-Aware Quantization for Diffusion Models
par: Zeng, Qian, et autres
Publié: (2025)

AdaLog: Post-Training Quantization for Vision Transformers with Adaptive Logarithm Quantizer
par: Wu, Zhuguanyu, et autres
Publié: (2024)

Punching Above Precision: Small Quantized Model Distillation with Learnable Regularizer
par: Rehman, Abdur, et autres
Publié: (2025)

Efficient INT8 Single-Image Super-Resolution via Deployment-Aware Quantization and Teacher-Guided Training
par: Nguyen, Pham Phuong Nam, et autres
Publié: (2026)

Enhancing Post-Training Quantization via Future Activation Awareness
par: Lv, Zheqi, et autres
Publié: (2026)

Diffusion Model Regularized Implicit Neural Representation for CT Metal Artifact Reduction
par: Wen, Jie, et autres
Publié: (2025)

Spatial-Regularization-Aware Dual-Branch Collaborative Inference for Training-Free OVSS in Remote Sensing Imagery
par: Wang, Jianzheng, et autres
Publié: (2026)