paper-with-me

Data Free Quantization

2개 벤치마크 · 논문 37편 · 이 태스크의 논문 보기 →

Benchmarks

CIFAR-100

결과 3개

CIFAR10

결과 3개

Most implemented

Papers

DVD-Quant: Data-free Video Diffusion Transformers Quantization

2025-05-24 · Zhiteng Li, Hanxuan Li, Junyi Wu, Kai Liu 외

Diffusion Transformers (DiTs) have emerged as the state-of-the-art architecture for video generation, yet their computational and memory demands hinder practical deployment. While post-training quantization (PTQ) present…

Data Free QuantizationQuantizationVideo Generation

OuroMamba: A Data-Free Quantization Framework for Vision Mamba Models

2025-03-13 · Akshat Ramachandran, Mingyu Lee, Huan Xu, Souvik Kundu 외

We present OuroMamba, the first data-free post-training quantization (DFQ) method for vision Mamba-based models (VMMs). We identify two key challenges in enabling DFQ for VMMs, (1) VMM's recurrent state transitions restr…

channel selectionContrastive LearningData Free QuantizationGPU+3

Enhancing Diversity for Data-free Quantization

2025-01-01 · CVPR 2025 1 · Kai Zhao, Zhihao Zhuang, Miao Zhang, Chenjuan Guo 외

Model quantization is an effective way to compress deep neural networks and accelerate the inference time on edge devices. Existing quantization methods usually require original data for calibration during the compre…

Data Free QuantizationDiversityQuantization

Semantics Prompting Data-Free Quantization for Low-Bit Vision Transformers

2024-12-21 · Yunshan Zhong, Yuyao Zhou, Yuxin Zhang, Shen Li 외

Data-free quantization (DFQ), which facilitates model quantization without real data to address increasing concerns about data security, has garnered significant attention within the model compression community. Recently…

Data Free QuantizationModel CompressionQuantization

Relation-Guided Adversarial Learning for Data-free Knowledge Transfer

2024-12-16 · Yingping Liang, Ying Fu

Data-free knowledge distillation transfers knowledge by recovering training data from a pre-trained model. Despite the recent success of seeking global data diversity, the diversity within each class and the similarity a…

Data-free Knowledge DistillationData Free QuantizationDiversityImage Generation+6

A method of using RSVD in residual calculation of LowBit GEMM

2024-09-27 · Hongyaoxing Gu

The advancements of hardware technology in recent years has brought many possibilities for low-precision applications. However, the use of low precision can introduce significant computational errors, posing a considerab…

Data Free QuantizationQuantization

전체 37편 보기 →