paper-with-me

Papers

SINCO: A Novel structural regularizer for image compression using implicit neural representations

2022-10-26 · Harry Gao, Weijie Gan, Zhixin Sun, Ulugbek S. Kamilov

Implicit neural representations (INR) have been recently proposed as deep learning (DL) based solutions for image compression. An image can be compressed by training an INR model with fewer weights than the number of image pixels to map the coordinates of the image to corresponding pixel values. While traditional training approaches for INRs are based on enforcing pixel-wise image consistency, we propose to further improve image quality by using a new structural regularizer. We present structural regularization for INR compression (SINCO) as a novel INR method for image compression. SINCO imposes structural consistency of the compressed images to the groundtruth by using a segmentation network to penalize the discrepancy of segmentation masks predicted from compressed images. We validate SINCO on brain MRI images by showing that it can achieve better performance than some recent INR methods.

📄 PDF Abstract BibTeX arXiv:2210.14974

Code (0)

등록된 구현이 없습니다.

Tasks

Image CompressionSegmentation

Similar Papers 제목 키워드 기반

Avoiding Structural Failure Modes in Tabular Fair SSL: Online Primal-Dual Allocation under Confidence Gating

2026-05-15 · Hangchuan Liang, Changchun Li arxiv

Semi-supervised learning (SSL) enables prediction with limited labels, but high-stakes tabular applications (medical, credit, recidivism) require statistical fairness guarantees. We identify a structural conflict in tabu…

An Information-Theoretic Regularizer for Lossy Neural Image Compression

2024-11-23 · Yingwen Zhang, Meng Wang, Xihua Sheng, Peilin Chen 외

Lossy image compression networks aim to minimize the latent entropy of images while adhering to specific distortion constraints. However, optimizing the neural network can be challenging due to its nature of learning qua…

Image Compression

Leveraging Visual Tokens for Extended Text Contexts in Multi-Modal Learning

2024-06-04 · Alex Jinpeng Wang, Linjie Li, Yiqi Lin, Min Li 외

Training models with longer in-context lengths is a significant challenge for multimodal model due to substantial GPU memory and computational costs. This exploratory study does not present state-of-the-art models; rathe…

document understandingGPURetrieval

In Situ Training of Implicit Neural Compressors for Scientific Simulations via Sketch-Based Regularization

2025-11-04 · Cooper Simpson, Stephen Becker, Alireza Doostan arxiv

Focusing on implicit neural representations, we present a novel in situ training protocol that employs limited memory buffers of full and sketched data samples, where the sketched data are leveraged to prevent catastroph…

Continual Learning

Map-Assisted Remote-Sensing Image Compression at Extremely Low Bitrates

2024-09-03 · Yixuan Ye, Ce Wang, Wanjie Sun, Zhenzhong Chen

Remote-sensing (RS) image compression at extremely low bitrates has always been a challenging task in practical scenarios like edge device storage and narrow bandwidth transmission. Generative models including VAEs and G…

Image Compression