paper-with-me

Papers

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

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

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 modeling still pose significant bottlenecks, limiting practical applications. Inspired by the effectiveness of state space models (SSMs) in capturing long-range dependencies, we leverage SSMs to address computational inefficiency in existing methods and improve image compression from multiple perspectives. In this paper, we integrate the advantages of SSMs for better efficiency-performance trade-off and propose an enhanced image compression approach through refined context modeling, which we term MambaIC. Specifically, we explore context modeling to adaptively refine the representation of hidden states. Additionally, we introduce window-based local attention into channel-spatial entropy modeling to reduce potential spatial redundancy during compression, thereby increasing efficiency. Comprehensive qualitative and quantitative results validate the effectiveness and efficiency of our approach, particularly for high-resolution image compression. Code is released at https://github.com/AuroraZengfh/MambaIC.

📄 PDF Abstract BibTeX arXiv:2503.12461

Code (1)

aurorazengfh/mambaic 공식 구현 pytorch

Tasks

Image CompressionState Space Models

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음

Similar Papers 제목 키워드 기반

Understanding Sample Generation Strategies for Learning Heuristic Functions in Classical Planning

2022-11-23 · R. V. Bettker, P. P. Minini, A. G. Pereira, M. Ritt

We study the problem of learning good heuristic functions for classical planning tasks with neural networks based on samples represented by states with their cost-to-goal estimates. The heuristic function is learned for …

Heuristic Search

A Survey of Learned Indexes for the Multi-dimensional Space

2024-03-11 · Abdullah Al-Mamun, Hao Wu, Qiyang He, Jianguo Wang 외

A recent research trend involves treating database index structures as Machine Learning (ML) models. In this domain, single or multiple ML models are trained to learn the mapping from keys to positions inside a data set.…

Survey

Adversarially Learned Anomaly Detection

2018-12-06 · Houssam Zenati, Manon Romain, Chuan Sheng Foo, Bruno Lecouat 외

Anomaly detection is a significant and hence well-studied problem. However, developing effective anomaly detection methods for complex and high-dimensional data remains a challenge. As Generative Adversarial Networks (GA…

Anomaly Detection

A Study on the Effect of Color Spaces in Learned Image Compression

2024-06-19 · Srivatsa Prativadibhayankaram, Mahadev Prasad Panda, Jürgen Seiler, Thomas Richter 외

In this work, we present a comparison between color spaces namely YUV, LAB, RGB and their effect on learned image compression. For this we use the structure and color based learned image codec (SLIC) from our prior work,…

Image CompressionMS-SSIMSSIM

LSI: A Learned Secondary Index Structure

2022-05-11 · Andreas Kipf, Dominik Horn, Pascal Pfeil, Ryan Marcus 외

Learned index structures have been shown to achieve favorable lookup performance and space consumption compared to their traditional counterparts such as B-trees. However, most learned index studies have focused on the p…