CVLGDec 23, 2019

FasterSeg: Searching for Faster Real-time Semantic Segmentation

arXiv:1912.10917v2208 citations
Originality Highly original
AI Analysis

This work addresses the need for efficient semantic segmentation models for real-time applications, such as autonomous driving, by introducing an automated design approach that improves speed without sacrificing performance.

The authors tackled the problem of designing a real-time semantic segmentation network that balances high accuracy and low latency, achieving over 30% faster speed than the closest manually designed competitor on Cityscapes while maintaining comparable accuracy.

We present FasterSeg, an automatically designed semantic segmentation network with not only state-of-the-art performance but also faster speed than current methods. Utilizing neural architecture search (NAS), FasterSeg is discovered from a novel and broader search space integrating multi-resolution branches, that has been recently found to be vital in manually designed segmentation models. To better calibrate the balance between the goals of high accuracy and low latency, we propose a decoupled and fine-grained latency regularization, that effectively overcomes our observed phenomenons that the searched networks are prone to "collapsing" to low-latency yet poor-accuracy models. Moreover, we seamlessly extend FasterSeg to a new collaborative search (co-searching) framework, simultaneously searching for a teacher and a student network in the same single run. The teacher-student distillation further boosts the student model's accuracy. Experiments on popular segmentation benchmarks demonstrate the competency of FasterSeg. For example, FasterSeg can run over 30% faster than the closest manually designed competitor on Cityscapes, while maintaining comparable accuracy.

Code Implementations2 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes