Mengyu Liu

Mengyu Liu, Hujun Yin

The spatial attention mechanism captures long-range dependencies by aggregating global contextual information to each query location, which is beneficial for semantic segmentation. In this paper, we present a sparse spatial attention network (SSANet) to improve the efficiency of the spatial attention mechanism without sacrificing the performance. Specifically, a sparse non-local (SNL) block is proposed to sample a subset of key and value elements for each query element to capture long-range relations adaptively and generate a sparse affinity matrix to aggregate contextual information efficiently. Experimental results show that the proposed approach outperforms other context aggregation methods and achieves state-of-the-art performance on the Cityscapes, PASCAL Context and ADE20K datasets.

Mengyu Liu, Hujun Yin

Although current deep learning methods have achieved impressive results for semantic segmentation, they incur high computational costs and have a huge number of parameters. For real-time applications, inference speed and memory usage are two important factors. To address the challenge, we propose a lightweight feature pyramid encoding network (FPENet) to make a good trade-off between accuracy and speed. Specifically, we use a feature pyramid encoding block to encode multi-scale contextual features with depthwise dilated convolutions in all stages of the encoder. A mutual embedding upsample module is introduced in the decoder to aggregate the high-level semantic features and low-level spatial details efficiently. The proposed network outperforms existing real-time methods with fewer parameters and improved inference speed on the Cityscapes and CamVid benchmark datasets. Specifically, FPENet achieves 68.0\% mean IoU on the Cityscapes test set with only 0.4M parameters and 102 FPS speed on an NVIDIA TITAN V GPU.

Mengyu Liu, Hujun Yin

In this paper, we address the semantic segmentation task with a deep network that combines contextual features and spatial information. The proposed Cross Attention Network is composed of two branches and a Feature Cross Attention (FCA) module. Specifically, a shallow branch is used to preserve low-level spatial information and a deep branch is employed to extract high-level contextual features. Then the FCA module is introduced to combine these two branches. Different from most existing attention mechanisms, the FCA module obtains spatial attention map and channel attention map from two branches separately, and then fuses them. The contextual features are used to provide global contextual guidance in fused feature maps, and spatial features are used to refine localizations. The proposed network outperforms other real-time methods with improved speed on the Cityscapes and CamVid datasets with lightweight backbones, and achieves state-of-the-art performance with a deep backbone.