EHANet: Efficient Hybrid Attention Network towards Real-time Semantic Segmentation
| Autor: | Weijie Mao, Wei Jiang, Zhenfeng Xue |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
050210 logistics & transportation
business.industry Computer science 05 social sciences Inference Pattern recognition 02 engineering and technology Image segmentation Visualization Feature (computer vision) 0502 economics and business 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Segmentation Artificial intelligence Representation (mathematics) business Encoder |
| Zdroj: | 2020 IEEE 6th International Conference on Computer and Communications (ICCC). |
| Popis: | Semantic segmentation suffers from the contradiction between inference speed and model accuracy. State-of-the-art real-time methods improve inference rapidity by sacrificing feature representation and model capacity. This paper proposes a novel Efficient Hybrid Attention Network (EHANet) to remedy this dilemma. The EHANet follows an encoder-decoder structure, where the encoder is composed of Reduced Basic-Block (RBB) with very few parameters. At decoding stages, a hybrid attention mechanism is designed to re-weight the feature map. The attention mechanism employs contextual attention for deep features and spatial attention for shallow features. The proposed architecture makes a trade off between inference speed and segmentation performance. As a result, the proposed model achieves 66.1% mIoU on the Cityscapes validation set. Meanwhile, it can operate at a speed of 113 FPS on one NVIDIA Titan XP GPU for an input image with size of $1024\times 512$ . |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|