Graph-guided Architecture Search for Real-time Semantic Segmentation

TL;DR

This paper introduces a Graph-guided Architecture Search (GAS) method that automatically designs real-time semantic segmentation networks, balancing accuracy and speed through a novel search space and graph convolution communication.

Contribution

The paper proposes a new search mechanism with a diverse cell-level design and latency constraints, integrating GCN for improved network exploration in semantic segmentation.

Findings

Achieves state-of-the-art accuracy-speed trade-off on Cityscapes.

GAS reaches 73.5% mIoU at 108.4 FPS on Titan Xp.

Outperforms previous methods in real-time segmentation benchmarks.

Abstract

Designing a lightweight semantic segmentation network often requires researchers to find a trade-off between performance and speed, which is always empirical due to the limited interpretability of neural networks. In order to release researchers from these tedious mechanical trials, we propose a Graph-guided Architecture Search (GAS) pipeline to automatically search real-time semantic segmentation networks. Unlike previous works that use a simplified search space and stack a repeatable cell to form a network, we introduce a novel search mechanism with new search space where a lightweight model can be effectively explored through the cell-level diversity and latencyoriented constraint. Specifically, to produce the cell-level diversity, the cell-sharing constraint is eliminated through the cell-independent manner. Then a graph convolution network (GCN) is seamlessly integrated as a communication mechanism between cells. Finally, a latency-oriented constraint is endowed into the search process to balance the speed and performance. Extensive experiments on Cityscapes and CamVid datasets demonstrate that GAS achieves the new state-of-the-art trade-off between accuracy and speed. In particular, on Cityscapes dataset, GAS achieves the new best performance of 73.5% mIoU with speed of 108.4 FPS on Titan Xp.