Easz: An Agile Transformer-based Image Compression Framework for Resource-constrained IoTs
Mao, Yu Li, Jingzong Wang, Jun Xu, Hong Kuo, Tei-Wei Wei Guan, Nan Xue, Chun Jason
Mao, Yu
Li, Jingzong
Wang, Jun
Xu, Hong
Kuo, Tei-Wei Wei
Guan, Nan
Xue, Chun Jason
Author
Supervisor
Department
Computer Science
Embargo End Date
Type
Conference proceeding
Date
2025
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Neural image compression, necessary in various machine-to-machine communication scenarios, suffers from its heavy encode-decode structures and inflexibility in switching between different compression levels. Consequently, it raises significant challenges in applying the neural image compression to edge devices that are developed for powerful servers with high computational and storage capacities. We take a step to solve the challenges by proposing a new transformer-based edge-computefree image coding framework called Easz. Easz shifts the computational overhead to the server, and hence avoids the heavy encoding and model switching overhead on the edge. Easz utilizes a patch-erase algorithm to selectively remove image contents using a conditional uniform-based sampler. The erased pixels are reconstructed on the receiver side through a transformer-based framework. To further reduce the computational overhead on the receiver, we then introduce a lightweight transformer-based reconstruction structure to reduce the reconstruction load on the receiver side. Extensive evaluations conducted on a realworld testbed demonstrate multiple advantages of Easz over existing compression approaches, in terms of adaptability to different compression levels, computational efficiency, and image reconstruction quality.
Co-author(s)
Citation
Y. Mao et al., "Easz: An Agile Transformer-based Image Compression Framework for Resource-constrained IoTs," 2025 62nd ACM/IEEE Design Automation Conference (DAC), San Francisco, CA, USA, 2025, pp. 1-7, doi: 10.1109/DAC63849.2025.11132645.
Source
Proceedings - Design Automation Conference
Conference
62nd ACM/IEEE Design Automation Conference, DAC 2025
Keywords
Erase-and-Squeeze, Image Compression, Transformer-based Auto-Encoder
Subjects
Source
62nd ACM/IEEE Design Automation Conference, DAC 2025
Publisher
IEEE