paper-with-me

Papers

A GAN-based Tunable Image Compression System

2020-01-18 · Lirong Wu, Kejie Huang, Haibin Shen

The method of importance map has been widely adopted in DNN-based lossy image compression to achieve bit allocation according to the importance of image contents. However, insufficient allocation of bits in non-important regions often leads to severe distortion at low bpp (bits per pixel), which hampers the development of efficient content-weighted image compression systems. This paper rethinks content-based compression by using Generative Adversarial Network (GAN) to reconstruct the non-important regions. Moreover, multiscale pyramid decomposition is applied to both the encoder and the discriminator to achieve global compression of high-resolution images. A tunable compression scheme is also proposed in this paper to compress an image to any specific compression ratio without retraining the model. The experimental results show that our proposed method improves MS-SSIM by more than 10.3% compared to the recently reported GAN-based method to achieve the same low bpp (0.05) on the Kodak dataset.

📄 PDF Abstract BibTeX arXiv:2001.06580

Code (0)

등록된 구현이 없습니다.

Tasks

Generative Adversarial NetworkImage CompressionMS-SSIMSSIM

Similar Papers 제목 키워드 기반

Mobiprox: Supporting Dynamic Approximate Computing on Mobiles

2023-03-16 · Matevž Fabjančič, Octavian Machidon, Hashim Sharif, Yifan Zhao 외

Runtime-tunable context-dependent network compression would make mobile deep learning (DL) adaptable to often varying resource availability, input "difficulty", or user needs. The existing compression techniques signific…

Activity RecognitionHuman Activity Recognition

A Novel Algorithm for Exact Concave Hull Extraction

2022-06-23 · Kevin Christopher VanHorn, Murat Can Çobanoğlu

Region extraction is necessary in a wide range of applications, from object detection in autonomous driving to analysis of subcellular morphology in cell biology. There exist two main approaches: convex hull extraction, …

Autonomous DrivingData CompressionImage Compressionobject-detection+2

Lossless and Near-Lossless Compression for Foundation Models

2024-04-05 · Moshik Hershcovitch, Leshem Choshen, Andrew Wood, Ilias Enmouri 외

With the growth of model sizes and scale of their deployment, their sheer size burdens the infrastructure requiring more network and more storage to accommodate these. While there is a vast literature about reducing mode…

SWAN: Sparse Winnowed Attention for Reduced Inference Memory via Decompression-Free KV-Cache Compression

2025-11-24 · Santhosh G S, Saurav Prakash, Balaraman Ravindran arxiv

Large Language Models (LLMs) face a significant bottleneck during autoregressive inference due to the massive memory footprint of the Key-Value (KV) cache. Existing compression techniques like token eviction, quantizatio…

Reconfiguring the Imaging Pipeline for Computer Vision

2017-05-11 · ICCV 2017 10 · Mark Buckler, Suren Jayasuriya, Adrian Sampson

Advancements in deep learning have ignited an explosion of research on efficient hardware for embedded computer vision. Hardware vision acceleration, however, does not address the cost of capturing and processing the ima…

Demosaicking