Presentation
LA-MTL: Latency-Aware Automated Multi-Task Learning
DescriptionMulti-Task Learning (MTL) unifies various tasks into a single network for improved training and inference efficiency, crucial for real-time applications in resource-constrained environments. Most MTL approaches enhance parameter efficiency and task metrics but lack explicit inference latency awareness. We propose LA-MTL, an automated layer-level MTL policy search incorporating a novel analytical latency factor (ALF), balancing task metrics, parameter efficiency, and latency constraints. LA-MTL on ResNet34 achieves up to 50% lower latency on Jetson AGX Orin with competitive metrics for semantic segmentation and depth estimation (+/-2 p.p.), on CityScapes, and surpasses state-of-the-art MTL parameters efficiency by 20 p.p. Code will be published upon acceptance
Event Type
Research Manuscript
TimeMonday, June 2311:45am - 12:00pm PDT
Location3000, Level 3
AI
AI1: AI/ML Algorithms