Chimera: Context-Aware Splittable Deep Multitasking Models for Edge Intelligence

Nimi, Sumaiya Tabassum; Arefeen, Md Adnan; Uddin, Yusuf Sarwar; Debnath, Biplob; Chakradhar, Srimat

doi:10.1109/smartcomp55677.2022.00025

Cited by 2 publications

(1 citation statement)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Various methods for solving complex segmentation and depth estimation-based multi-task learning are discussed in the literature [4,31,40]. A knowledge distillation technique is proposed by Liu et al [23] specifically for semantic segmentation tasks.…”

Section: Related Workmentioning

confidence: 99%

MetaMorphosis: Task-oriented Privacy Cognizant Feature Generation for Multi-task Learning

Arefeen

Uddin

et al. 2023

Proceedings of the 8th ACM/IEEE Conference on Internet of Things Design and Implementation

Self Cite

View full text Add to dashboard Cite

With the growth of computer vision applications, deep learning, and edge computing contribute to ensuring practical collaborative intelligence (CI) by distributing the workload among edge devices and the cloud. However, running separate single-task models on edge devices is inefficient regarding the required computational resource and time. In this context, multitask learning allows leveraging a single deep learning model for performing multiple tasks, such as semantic segmentation and depth estimation on incoming video frames. This single processing pipeline generates common deep features that are shared among multi-task modules. However, in a collaborative intelligence scenario, generating common deep features has two major issues. First, the deep features may inadvertently contain input information exposed to the downstream modules (violating input privacy). Second, the generated universal features expose a piece of collective information than what is intended for a certain task, in which features for one task can be utilized to perform another task (violating task privacy). This paper proposes a novel deep learning-based privacy-cognizant feature generation process called "MetaMorphosis" that limits inference capability to specific tasks at hand. To achieve this, we propose a channel squeeze-excitation based feature metamorphosis module, Cross-SEC, to achieve distinct attention of all tasks and a de-correlation loss function with differential-privacy to train a deep learning model that produces distinct privacy-aware features as an output for the respective tasks. With extensive experimentation on four datasets consisting of diverse images related to scene understanding and facial attributes, we show that MetaMorphosis outperforms recent adversarial learning and universal feature generation methods by guaranteeing privacy requirements in an efficient way for image and video analytics. CCS Concepts: • Computing methodologies → Computer vision tasks; Scene understanding; • Security and privacy → Privacy protections.

show abstract