Accelerating Learned Image Compression Through Modeling Neural Training Dynamics
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Image CompressionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Accelerating block-level rate control for learned image compression
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 CompressionFeedback Recurrent Autoencoder for Video Compression
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 CompressionMambaIC: State Space Models for High-Performance Learned Image Compression
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 ModelsHiDE: Hierarchical Dictionary-Based Entropy Modeling for Learned Image Compression
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 CompressionLinear Attention Modeling for Learned Image Compression
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