paper-with-me

Papers

Accelerating Learned Image Compression Through Modeling Neural Training Dynamics

2025-05-23 · Yichi Zhang, Zhihao Duan, Yuning Huang, Fengqing Zhu

As learned image compression (LIC) methods become increasingly computationally demanding, enhancing their training efficiency is crucial. This paper takes a step forward in accelerating the training of LIC methods by modeling the neural training dynamics. We first propose a Sensitivity-aware True and Dummy Embedding Training mechanism (STDET) that clusters LIC model parameters into few separate modes where parameters are expressed as affine transformations of reference parameters within the same mode. By further utilizing the stable intra-mode correlations throughout training and parameter sensitivities, we gradually embed non-reference parameters, reducing the number of trainable parameters. Additionally, we incorporate a Sampling-then-Moving Average (SMA) technique, interpolating sampled weights from stochastic gradient descent (SGD) training to obtain the moving average weights, ensuring smooth temporal behavior and minimizing training state variances. Overall, our method significantly reduces training space dimensions and the number of trainable parameters without sacrificing model performance, thus accelerating model convergence. We also provide a theoretical analysis on the Noisy quadratic model, showing that the proposed method achieves a lower training variance than standard SGD. Our approach offers valuable insights for further developing efficient training methods for LICs.

📄 PDF Abstract BibTeX arXiv:2505.18107

Code (0)

등록된 구현이 없습니다.

Tasks

Image Compression

Methods 이 논문이 사용한 방법론

SGD Stochastic Gradient Descent is an iterative optimization technique that uses minibatches of data to form an expectation of the gradient, rather than the full gradient using…

Similar Papers 제목 키워드 기반

Accelerating block-level rate control for learned image compression

2024-09-02 · Muchen Dong, Ming Lu, Zhan Ma

Despite the unprecedented compression efficiency achieved by deep learned image compression (LIC), existing methods usually approximate the desired bitrate by adjusting a single quality factor for a given input image, wh…

Image Compression

Feedback Recurrent Autoencoder for Video Compression

2020-04-09 · Adam Golinski, Reza Pourreza, Yang Yang, Guillaume Sautiere 외

Recent advances in deep generative modeling have enabled efficient modeling of high dimensional data distributions and opened up a new horizon for solving data compression problems. Specifically, autoencoder based learne…

Data CompressionMS-SSIMSSIMVideo Compression

MambaIC: State Space Models for High-Performance Learned Image Compression

2025-03-16 · CVPR 2025 1 · Fanhu Zeng, Hao Tang, Yihua Shao, Siyu Chen 외

A high-performance image compression algorithm is crucial for real-time information transmission across numerous fields. Despite rapid progress in image compression, computational inefficiency and poor redundancy modelin…

Image CompressionState Space Models

HiDE: Hierarchical Dictionary-Based Entropy Modeling for Learned Image Compression

2026-03-06 · Haoxuan Xiong, Yuanyuan Xu, Kun Zhu, Yiming Wang 외 arxiv

Learned image compression (LIC) has achieved remarkable coding efficiency, where entropy modeling plays a pivotal role in minimizing bitrate through informative priors. Existing methods predominantly exploit internal con…

Image Compression

Linear Attention Modeling for Learned Image Compression

2025-02-09 · CVPR 2025 1 · Donghui Feng, Zhengxue Cheng, Shen Wang, Ronghua Wu 외

Recent years, learned image compression has made tremendous progress to achieve impressive coding efficiency. Its coding gain mainly comes from non-linear neural network-based transform and learnable entropy modeling. Ho…

Image Compression