paper-with-me

홈 › Papers

DynaQuant: Dynamic Mixed-Precision Quantization for Learned Image Compression

2025-11-11 · Youneng Bao, Yulong Cheng, Yiping Liu, Yichen Yang, Peng Qin, Mu Li, Yongsheng Liang arxiv

Prevailing quantization techniques in Learned Image Compression (LIC) typically employ a static, uniform bit-width across all layers, failing to adapt to the highly diverse data distributions and sensitivity characteristics inherent in LIC models. This leads to a suboptimal trade-off between performance and efficiency. In this paper, we introduce DynaQuant, a novel framework for dynamic mixed-precision quantization that operates on two complementary levels. First, we propose content-aware quantization, where learnable scaling and offset parameters dynamically adapt to the statistical variations of latent features. This fine-grained adaptation is trained end-to-end using a novel Distance-aware Gradient Modulator (DGM), which provides a more informative learning signal than the standard Straight-Through Estimator. Second, we introduce a data-driven, dynamic bit-width selector that learns to assign an optimal bit precision to each layer, dynamically reconfiguring the network's precision profile based on the input data. Our fully dynamic approach offers substantial flexibility in balancing rate-distortion (R-D) performance and computational cost. Experiments demonstrate that DynaQuant achieves rd performance comparable to full-precision models while significantly reducing computational and storage requirements, thereby enabling the practical deployment of advanced LIC on diverse hardware platforms.

📄 PDF Abstract BibTeX arXiv:2511.07903

Code (0)

등록된 구현이 없습니다.

Tasks

Image Compression

Similar Papers 제목 키워드 기반

DynaQuant: Compressing Deep Learning Training Checkpoints via Dynamic Quantization

2023-06-20 · Amey Agrawal, Sameer Reddy, Satwik Bhattamishra, Venkata Prabhakara Sarath Nookala 외

With the increase in the scale of Deep Learning (DL) training workloads in terms of compute resources and time consumption, the likelihood of encountering in-training failures rises substantially, leading to lost work an…

Deep LearningModel CompressionQuantizationTransfer Learning

Data Quality-aware Mixed-precision Quantization via Hybrid Reinforcement Learning

2023-02-09 · Yingchun Wang, Jingcai Guo, Song Guo, Weizhan Zhang

Mixed-precision quantization mostly predetermines the model bit-width settings before actual training due to the non-differential bit-width sampling process, obtaining sub-optimal performance. Worse still, the convention…

Quantizationreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Mixed Precision of Quantization of Transformer Language Models for Speech Recognition

2021-11-29 · Junhao Xu, Shoukang Hu, Jianwei Yu, Xunying Liu 외

State-of-the-art neural language models represented by Transformers are becoming increasingly complex and expensive for practical applications. Low-bit deep neural network quantization techniques provides a powerful solu…

QuantizationSensitivityspeech-recognitionSpeech Recognition

CSQ: Growing Mixed-Precision Quantization Scheme with Bi-level Continuous Sparsification

2022-12-06 · Lirui Xiao, Huanrui Yang, Zhen Dong, Kurt Keutzer 외

Mixed-precision quantization has been widely applied on deep neural networks (DNNs) as it leads to significantly better efficiency-accuracy tradeoffs compared to uniform quantization. Meanwhile, determining the exact pre…

Quantization

Mixed Precision DNNs: All you need is a good parametrization

2019-05-27 · ICLR 2020 1 · Stefan Uhlich, Lukas Mauch, Fabien Cardinaux, Kazuki Yoshiyama 외

Efficient deep neural network (DNN) inference on mobile or embedded devices typically involves quantization of the network parameters and activations. In particular, mixed precision networks achieve better performance th…

AllQuantization