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

TL;DR

This paper introduces LGCNet, a neural architecture search framework for real-time semantic segmentation that effectively balances accuracy and speed by employing a new search space and local-to-global information communication modules.

Contribution

The paper proposes a novel search space with cell-independent architecture and two communication modules for local and global information exchange, improving real-time segmentation performance.

Findings

Achieves 74.0% mIoU on Cityscapes with 115.2 FPS

Outperforms previous methods in accuracy-speed trade-off

Demonstrates effectiveness on Cityscapes and CamVid datasets

Abstract

Neural Architecture Search (NAS) has shown great potentials in automatically designing neural network architectures for real-time semantic segmentation. Unlike previous works that utilize a simplified search space with cell-sharing way, we introduce a new search space where a lightweight model can be more effectively searched by replacing the cell-sharing manner with cell-independent one. Based on this, the communication of local to global information is achieved through two well-designed modules. For local information exchange, a graph convolutional network (GCN) guided module is seamlessly integrated as a communication deliver between cells. For global information aggregation, we propose a novel dense-connected fusion module (cell) which aggregates long-range multi-level features in the network automatically. In addition, a latency-oriented constraint is endowed into the search process to balance the accuracy and latency. We name the proposed framework as Local-to-Global Information Communication Network Search (LGCNet). Extensive experiments on Cityscapes and CamVid datasets demonstrate that LGCNet achieves the new state-of-the-art trade-off between accuracy and speed. In particular, on Cityscapes dataset, LGCNet achieves the new best performance of 74.0\% mIoU with the speed of 115.2 FPS on Titan Xp.