Vision Transformer for Semantic Image Compression
Paper Title:
Transformer-Aided Semantic Communications
Published on:
2 May 2024
Primary Category:
Computer Vision and Pattern Recognition
Paper Authors:
Matin Mortaheb,
Erciyes Karakaya,
Mohammad A. Amir Khojastepour,
Sennur Ulukus
Bullets
Key Details
Employs vision transformers for semantic image compression under bandwidth constraints
Creates attention mask to prioritize critical image segments for transmission
Encodes image parts according to semantic information content
Optimizes bandwidth usage while preserving semantics
Evaluation shows preserved semantics even with high compression rates
Explore the topics in this paper
AI generated summary
Vision Transformer for Semantic Image Compression
This paper proposes a novel framework for semantic image communication using vision transformers. It creates an attention mask to prioritize critical image segments for transmission, ensuring reconstruction focuses on key objects. This significantly improves semantic communication quality and bandwidth efficiency by encoding parts proportional to semantic content. Evaluated on TinyImageNet, it succeeds in preserving semantics even when transmitting a fraction of encoded data.
Answers from this paper
You might also like
Efficient image transmission through neural networks
Efficient image communication for AIoT using deep semantic segmentation and restoration
Efficient vision transformers for semantic segmentation
Lightweight clustering for semantic segmentation
Efficient semantic segmentation with a single CNN
Semantic face image generation preserving identity
Comments
No comments yet, be the first to start the conversation...
Sign up to comment on this paper