Graph-Guided Architecture Search for Real-Time Semantic Segmentation

By Peiwen Lin, Guangliang Cheng, Sirui Xie, Xi Li, Jianping Shi. 2019

108 citations recorded by the source corpus.

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 a new search space where a lightweight model can be effectively explored through the cell-level diversity and latency oriented 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 the speed of 108.4 FPS on Titan Xp.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Lu Yuan
2. Bin Xiao
3. Jingdong Wang
4. Lei Zhang
5. Changqian Yu
6. Chen Qian
7. Fei Wang
8. Changxin Gao

In Computer Vision and Pattern Recognition

1. Dacheng Tao
2. Luc Van Gool
3. Jingdong Wang
4. Yi Yang
5. Lu Yuan
6. Chunhua Shen
7. Ming-Hsuan Yang
8. Xiaogang Wang

Citations in the corpus

• GreedyNAS: Towards Fast One-Shot NAS With Greedy Supernet (2020, background): “In contrast, neural architecture search (NAS) aims at automatically learning the network architecture to further boost the performance for target tasks [10, 20, 43, 2, 19].”
• Efficient Architecture Search for Continual Learning (2020, background): “Apart from algorithms, NAS also has many valuable applications. such as image classification [30], [31], video segmentation [32], [33], and text representation [34].”
• Lite-HRNet: A Lightweight High-Resolution Network (2021, methodology): “02 GFLOPs, outperforming the hand-crafted methods [34, 55, 50, 23, 58, 36, 41, 12] and NAS-based methods [54, 25, 16, 24] , and comparable with SwiftNetRN18 [32] that is far computationally intensive (104 GFLOPs).”
• Rethinking BiSeNet For Real-time Semantic Segmentation (2021, methodology): “The prosperity of deep learning greatly promotes the performance of semantic segmentation by making various breakthroughs [18, 27, 22, 4], coming with fast-growing demands in many applications, e.”
• Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes (2021, methodology): “It is worth noting that our method also towers over those methods based on architecture search for real-time semantic segmentation such as CAS [47] and GAS [48] with similar inference speed.”