TrustServing: A Quality Inspection Sampling Approach for Remote DNN Services

Hou, Xueyu

doi:10.1109/secon48991.2020.9158444

Cited by 8 publications

(2 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Even for the 2D case, it is well-known that the high latency caused by DNN inference negatively impacts the quality of user experience [3,25]. A widely-used acceleration technique is to offload the compute-heavy tasks to cloud/edge servers [26,38,72], which is also a promising solution to speed up 3D object detection. However, we find that even with the help of a powerful GPU, the inference time of 3D object detection ranges from 72 to 283 ms ( §2.3).…”

Section: Introductionmentioning

confidence: 99%

DeepMix

Guan

Hou

et al. 2022

Proceedings of the 20th Annual International Conference on Mobile Systems, Applications and Services

Self Cite

View full text Add to dashboard Cite

Mobile headsets should be capable of understanding 3D physical environments to offer a truly immersive experience for augmented/mixed reality (AR/MR). However, their small form-factor and limited computation resources make it extremely challenging to execute in real-time 3D vision algorithms, which are known to be more compute-intensive than their 2D counterparts. In this paper, we propose DeepMix, a mobility-aware, lightweight, and hybrid 3D object detection framework for improving the user experience of AR/MR on mobile headsets. Motivated by our analysis and evaluation of state-of-the-art 3D object detection models, DeepMix intelligently combines edge-assisted 2D object detection and novel, on-device 3D bounding box estimations that leverage depth data captured by headsets. This leads to low end-to-end latency and significantly boosts detection accuracy in mobile scenarios. A unique feature of DeepMix is that it fully exploits the mobility of headsets to fine-tune detection results and boost detection accuracy. To the best of our knowledge, DeepMix is the first 3D object detection that achieves 30 FPS (i.e., an end-to-end latency much lower than the 100 ms stringent requirement of interactive AR/MR). We implement a prototype of DeepMix on Microsoft HoloLens and evaluate its performance via both extensive controlled experiments and a user study with 30+ participants. DeepMix not only improves detection accuracy by 9.1-37.3% but also reduces end-to-end latency by 2.68-9.15⇥, compared to the baseline that uses existing 3D object detection models. CCS CONCEPTS• Human-centered computing ! Ubiquitous and mobile computing systems and tools; Systems and tools for interaction design.

show abstract

Section: Introductionmentioning

confidence: 99%

DeepMix

Guan

Hou

et al. 2022

Proceedings of the 20th Annual International Conference on Mobile Systems, Applications and Services

Self Cite

View full text Add to dashboard Cite

show abstract

“…First, explainable DNN, which achieves high accuracy for reliable satellite image analysis, requires high computational complexity. In general, higher inference accuracy can be achieved with a deeper and wider network containing a greater number of network layers and channels [3]. These features significantly increase the computing complexity and memory access complexity that sophisticated hardware accelerators are required to address.…”

Section: Introductionmentioning

confidence: 99%

Cooperative Scheduling Schemes for Explainable DNN Acceleration in Satellite Image Analysis and Retraining

Kim

Youn

2022

IEEE Trans. Parallel Distrib. Syst.

View full text Add to dashboard Cite

The deep learning-based satellite image analysis and retraining systems are getting emerging technologies to enhance the capability of the sophisticated analysis of terrestrial objects. In principle, to apply the explainable DNN model for the process of satellite image analysis and retraining, we consider a new acceleration scheduling mechanism. Especially, the conventional DNN acceleration schemes cause serious performance degradation due to computational complexity and costs in satellite image analysis and retraining. In this article, to overcome the performance degradation, we propose cooperative scheduling schemes for explainable DNN acceleration in analysis and retraining process. For the purpose of it, we define the latency and energy cost modeling to derive the optimized processing time and cost required for explainable DNN acceleration. Especially, we show a minimum processing cost considered in the proposed scheduling via layer-level management of the explainable DNN on FPGA-GPU acceleration system. In addition, we evaluate the performance using an adaptive unlabeled data selection scheme with confidence threshold and a semi-supervised learning driven data parallelism scheme in accelerating retraining process. The experimental results demonstrate that the proposed schemes reduce the energy cost of the conventional DNN acceleration systems by up to about 40% while guaranteeing the latency constraints.

show abstract