Recursive Vision Transformer with Dynamic Depth and Width Adjustment for Resource-Efficient Image Semantic Communication
Quick Take
The proposed recursive Vision Transformer (ViT) system for image semantic communication reduces parameters by 48.7% while enhancing reconstruction quality through dynamic depth and width adjustments. This innovation addresses the challenges of high memory and computational demands, making it suitable for resource-constrained devices.
Key Points
- Introduces a recursive structure to refine semantic features and lower parameter count.
- Dynamic depth adjustment adapts to image content and channel conditions.
- Dynamic width adjustment preserves important neurons and attention heads.
- Joint width-depth optimization allows flexible computation configurations.
- Simulation results show improved reconstruction quality over existing baselines.
Article Content
From source RSS / original summaryarXiv:2606. 00114v1 Announce Type: new Abstract: Image semantic communication is a critical component in next-generation wireless communication systems. However, such systems typically suffer from large memory footprints and high computational complexity, making them difficult to deploy on resource-constrained devices. To address these challenges, we propose a vision transformer (ViT)-enabled image semantic communication system.
In this system, a recursive structure is introduced to iteratively refine semantic features and reduce the parameter count. In addition, three dynamic adjustment strategies are designed to adaptively reduce computational complexity: dynamic depth adjustment, dynamic width adjustment, and joint width-depth optimization.
Dynamic depth adjustment adaptively determines the number of recursive modules according to image content and channel conditions, while dynamic width adjustment selectively preserves important neurons and attention heads. The joint width-depth optimization further enables flexible computation configurations. Simulation results verify that the proposed recursive ViT-based system, combined with the three dynamic adjustment strategies, reduces the parameter count by 48.
7% and achieves higher reconstruction quality than existing baselines under comparable computational complexity.
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →Evi-Steer: Learning to Steer Biomedical Vision-Language Models through Efficient and Generalizable Evidential Tuning
Evi-Steer introduces a novel evidential tuning framework for BiomedCLIP, enabling efficient fine-tuning with only 0.11% parameter updates. It significantly enhances performance in few-shot learning and domain shifts across 15 biomedical imaging datasets, demonstrating robustness for clinical applications.
