Federated Onboard-Ground Station Computing With Weakly Supervised Cascading Pyramid Attention Network for Satellite Image Analysis

Kim, Taewoo; Jeon, Minsu; Lee, Changha; Kim, Junsoo; Ko, Geonwoo; Kim, Joo-Young; Youn, Chan‐Hyun

doi:10.1109/access.2022.3219879

Cited by 6 publications

(5 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to evaluate the feasibility of the proposed methods on the restricted computing environments such as satellite on-board computing system [11], the embedded system board [31] in which inference of the deep learning models can be served in low power management is used as a test environment. Fig.…”

Section: Feasibility Of DL Serving With Pruning 1) Practical Environm...mentioning

confidence: 99%

“…Fig. 10 shows the hardware prototype of our embedded system board [31], and it consists of NVIDIA Jetson Nano chipset for managing host/GPU and ASIC chip that is designed to process the inference of the deep learning models. In the system, 4GB DDR4 memory is available, and ASIC chip is prototyped under Samsung foundry 28-nm CMOS process with 200mW power consumption and minimum 7.5W in the entire on-board system.…”

Section: Feasibility Of DL Serving With Pruning 1) Practical Environm...mentioning

confidence: 99%

“…The custom ASIC chip [31] mainly consists of shared memory and convolutional/vector processor, and it interworks with the programmable logic controller and the external memory to process the DL inference task. In the programmable logic controller, the task of DL inference is partitioned into subtasks of size that the intrinsic resources can accommodate, and the subtasks are processed sequentially.…”

Section: Feasibility Of DL Serving With Pruning 1) Practical Environm...mentioning

confidence: 99%

“…After processing each subtask, programmable logic controller loads the results from the shared memory of ASIC chip to external memory. Further details of the prototype onboard system are provided in [31].…”

Section: Feasibility Of DL Serving With Pruning 1) Practical Environm...mentioning

confidence: 99%

“…FIGURE 10. Developed of on-board system[31] with proposed layer-wise channel pruning optimization model.…”

mentioning

confidence: 99%

See 4 more Smart Citations

A Channel Pruning Optimization With Layer-Wise Sensitivity in a Single-Shot Manner Under Computational Constraints

et al. 2023

Self Cite

View full text Add to dashboard Cite

In the constrained computing environments such as mobile device or satellite on-board system, various computational factors of hardware resource can restrict the processing of deep learning (DL) services.Recent DL models such as satellite image analysis mainly require larger resource memory occupation for intermediate feature map footprint than the given memory specification of hardware resource and larger computational overhead (in FLOP) to meet service-level objective in the sense of hardware accelerator. As one of the solutions, we propose a new method of controlling the layer-wise channel pruning in a single-shot manner that can decide how much channels to prune in each layer by observing dataset once without full pretraining. To improve the robustness of the performance degradation, we also propose a layer-wise sensitivity and formulate the optimization problems for deciding layer-wise pruning ratio under target computational constraints. In the paper, the optimal conditions are theoretically derived, and the practical optimum searching schemes are proposed using the optimal conditions. On the empirical evaluation, the proposed methods show robustness on performance degradation, and present feasibility on DL serving under constrained computing environments by reducing memory occupation, providing acceleration effect and throughput improvement while keeping the accuracy performance.INDEX TERMS Single-shot pruning, channel pruning, lottery ticket hypothesis, DL model compression.

show abstract

Section: Feasibility Of DL Serving With Pruning 1) Practical Environm...mentioning

confidence: 99%

Section: Feasibility Of DL Serving With Pruning 1) Practical Environm...mentioning

confidence: 99%

Section: Feasibility Of DL Serving With Pruning 1) Practical Environm...mentioning

confidence: 99%

Section: Feasibility Of DL Serving With Pruning 1) Practical Environm...mentioning

confidence: 99%

“…FIGURE 10. Developed of on-board system[31] with proposed layer-wise channel pruning optimization model.…”

mentioning

confidence: 99%

See 3 more Smart Citations

A Channel Pruning Optimization With Layer-Wise Sensitivity in a Single-Shot Manner Under Computational Constraints

et al. 2023

Self Cite

View full text Add to dashboard Cite

show abstract

Decrypting Disruptive Technologies: Review and Research Agenda of Explainable AI as a Game Changer

Dabas,

Thomas,

Khatri

et al. 2023

2023 IEEE International Conference on Technology Management, Operations and Decisions (ICTMOD)

View full text Add to dashboard Cite

EPU: An Energy-Efficient Explainable AI Accelerator With Sparsity-Free Computation and Heat Map Compression/Pruning

Kim,

Han,

et al. 2024

IEEE J. Solid-State Circuits

View full text Add to dashboard Cite

Federated Onboard-Ground Station Computing With Weakly Supervised Cascading Pyramid Attention Network for Satellite Image Analysis

Cited by 6 publications

References 36 publications

A Channel Pruning Optimization With Layer-Wise Sensitivity in a Single-Shot Manner Under Computational Constraints

A Channel Pruning Optimization With Layer-Wise Sensitivity in a Single-Shot Manner Under Computational Constraints

Decrypting Disruptive Technologies: Review and Research Agenda of Explainable AI as a Game Changer

EPU: An Energy-Efficient Explainable AI Accelerator With Sparsity-Free Computation and Heat Map Compression/Pruning

Contact Info

Product

Resources

About