A multitask deep learning model for real-time deployment in embedded systems
We propose an approach to Multitask Learning (MTL) to make deep learning models faster and lighter for applications in which multiple tasks need to be solved simultaneously, which is particularly useful in embedded, real-time systems. We develop a multitask model for both Object Detection and Semantic Segmentation and analyze the challenges that appear during its training. Our multitask network is 1.6x faster, lighter and uses less memory than deploying the single-task models in parallel. We conclude that MTL has the potential to give superior performance in exchange of a more complex training process that introduces challenges not present in single-task models.
Code (0)
등록된 구현이 없습니다.
Tasks
object-detectionObject DetectionSemantic SegmentationSimilar Papers 제목 키워드 기반
QuadBEV: An Efficient Quadruple-Task Perception Framework via Bird's-Eye-View Representation
Bird's-Eye-View (BEV) perception has become a vital component of autonomous driving systems due to its ability to integrate multiple sensor inputs into a unified representation, enhancing performance in various downstrea…
3D Object DetectionAutonomous DrivingLane Detectionobject-detection+1LoopNet: A Multitasking Few-Shot Learning Approach for Loop Closure in Large Scale SLAM
One of the main challenges in the Simultaneous Localization and Mapping (SLAM) loop closure problem is the recognition of previously visited places. In this work, we tackle the two main problems of real-time SLAM systems…
Few-Shot LearningMulti-Task Network Pruning and Embedded Optimization for Real-time Deployment in ADAS
Camera-based Deep Learning algorithms are increasingly needed for perception in Automated Driving systems. However, constraints from the automotive industry challenge the deployment of CNNs by imposing embedded systems w…
Network Pruningobject-detectionObject DetectionQuantization+1ProAI: An Efficient Embedded AI Hardware for Automotive Applications -- a Benchmark Study
Development in the field of Single Board Computers (SBC) have been increasing for several years. They provide a good balance between computing performance and power consumption which is usually required for mobile platfo…
Autonomous DrivingCPUGPUReal-Time Performance Benchmarking of TinyML Models in Embedded Systems (PICO: Performance of Inference, CPU, and Operations)
This paper presents PICO-TINYML-BENCHMARK, a modular and platform-agnostic framework for benchmarking the real-time performance of TinyML models on resource-constrained embedded systems. Evaluating key metrics such as in…
Keyword Spotting