Context-Integrated and Feature-Refined Network for Lightweight Object Parsing

Semantic segmentation for lightweight object parsing is a very challenging task, because both accuracy and efficiency (e.g., execution speed, memory footprint, or computational complexity) should all be taken into account. However, most previous works pay too much attention to one-sided perspective, either accuracy or speed, and ignore others, which poses a great limitation to actual demands of intelligent devices. To tackle this dilemma, we propose a new lightweight architecture named Context-Integrated and Feature-Refined Network (CIFReNet). The core components of CIFReNet are the Long-skip Refinement Module (LRM) and the Multi-scale Contexts Integration Module (MCIM). The LRM is designed to ease the propagation of spatial information between low-level and high-level layers. Furthermore, channel attention mechanism is introduced into the long skip connection to boost the quality of low-level feature refinement. Meanwhile, the MCIM consists of three cascaded Dense Semantic Pyramid (DSP) blocks with image-level features, which is presented to encode multiple contexts and enlarge the field of view. The proposed DSP block exploits a denser feature sampling strategy to enhance the information representations without significantly increasing the computation cost. Comprehensive experiments are conducted on three object parsing datasets including Cityscapes, Camvid, and Helen. The results have demonstrated that our proposed method reaches a better trade-off between accuracy and efficiency compared with the other state-of-the-art methods.