FasterSeg: Searching for Faster Real-time Semantic Segmentation

12/23/2019
by   Wuyang Chen, et al.
0

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 than the closest manually designed competitor on Cityscapes, while maintaining comparable accuracy.

READ FULL TEXT
research
08/05/2019

SqueezeNAS: Fast neural architecture search for faster semantic segmentation

For real time applications utilizing Deep Neural Networks (DNNs), it is ...
research
08/10/2022

Efficient Joint-Dimensional Search with Solution Space Regularization for Real-Time Semantic Segmentation

Semantic segmentation is a popular research topic in computer vision, an...
research
03/16/2023

Neural Architecture Search for Effective Teacher-Student Knowledge Transfer in Language Models

Large pre-trained language models have achieved state-of-the-art results...
research
02/16/2023

Local-to-Global Information Communication for Real-Time Semantic Segmentation Network Search

Neural Architecture Search (NAS) has shown great potentials in automatic...
research
05/06/2019

Searching for MobileNetV3

We present the next generation of MobileNets based on a combination of c...
research
09/15/2019

Graph-guided Architecture Search for Real-time Semantic Segmentation

Designing a lightweight semantic segmentation network often requires res...
research
03/28/2023

FMAS: Fast Multi-Objective SuperNet Architecture Search for Semantic Segmentation

We present FMAS, a fast multi-objective neural architecture search frame...

Please sign up or login with your details

Forgot password? Click here to reset