TL;DR
This paper introduces a benchmark test suite, CitySeg/MOP, for multi-objective optimization in hardware-aware neural architecture search for real-time semantic segmentation, facilitating evaluation of algorithms balancing accuracy, speed, and hardware constraints.
Contribution
It develops a novel benchmark suite, CitySeg/MOP, transforming HW-NAS for semantic segmentation into standard multi-objective problems and integrating it into the EvoXBench platform.
Findings
Benchmark suite covers 15 MOPs from Cityscapes dataset.
Demonstrates versatility across various multi-objective evolutionary algorithms.
Provides seamless interface for fitness evaluations in multiple programming languages.
Abstract
As one of the emerging challenges in Automated Machine Learning, the Hardware-aware Neural Architecture Search (HW-NAS) tasks can be treated as black-box multi-objective optimization problems (MOPs). An important application of HW-NAS is real-time semantic segmentation, which plays a pivotal role in autonomous driving scenarios. The HW-NAS for real-time semantic segmentation inherently needs to balance multiple optimization objectives, including model accuracy, inference speed, and hardware-specific considerations. Despite its importance, benchmarks have yet to be developed to frame such a challenging task as multi-objective optimization. To bridge the gap, we introduce a tailored streamline to transform the task of HW-NAS for real-time semantic segmentation into standard MOPs. Building upon the streamline, we present a benchmark test suite, CitySeg/MOP, comprising fifteen MOPs derived…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
