Semantic Flow for Fast and Accurate Scene Parsing
By Xiangtai Li, Ansheng You, Zhen Zhu, Houlong Zhao, Maoke Yang, Kuiyuan Yang, Yunhai Tong. European Conference on Computer Vision, 2020
448 citations recorded by the source corpus.
In this paper, we focus on designing effective method for fast and accurate scene parsing. A common practice to improve the performance is to attain high resolution feature maps with strong semantic representation. Two strategies are widely used---atrous convolutions and feature pyramid fusion, are either computation intensive or ineffective. Inspired by the Optical Flow for motion alignment between adjacent video frames, we propose a Flow Alignment Module (FAM) to learn Semantic Flow between feature maps of adjacent levels, and broadcast high-level features to high resolution features effectively and efficiently. Furthermore, integrating our module to a common feature pyramid structure exhibits superior performance over other real-time methods even on light-weight backbone networks, such as ResNet-18. Extensive experiments are conducted on several challenging datasets, including Cityscapes, PASCAL Context, ADE20K and CamVid. Especially, our network is the first to achieve 80.4\% mIoU on Cityscapes with a frame rate of 26 FPS. The code is available at \url{this https URL}.
Subfields: Computer Vision and Pattern Recognition
View Paper: https://www.semanticscholar.org/paper/01831d9b657e011fb3d6d713f42001ccab9b769c
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Chen Change Loy
- Kai Chen
- Ziwei Liu
- Luc Van Gool
- Jiangmiao Pang
- Xiaogang Wang
- Henghui Ding
- Dacheng Tao
Citations in the corpus
- Deep Dual-Resolution Networks for Real-Time and Accurate Semantic Segmentation of Traffic Scenes (2023, methodology): “One utilizes the GPU-efficient backbones, especially ResNet-18 [20], [21], [22].”
- YOLOv4-5D: An Effective and Efficient Object Detector for Autonomous Driving (2021, background): “Object detection and semantic segmentation algorithms based on deep learning have become extremely important in the field of autonomous driving [36].”
- Transformer-Based Visual Segmentation: A Survey (2023, methodology): “…including better encoder-decoder frameworks [58], [59], larger kernels [60], [61], multiscale pooling [11], [62], multiscale feature fusion [12], [63], [64], [65], non-local modeling [18], [66], [67], efficient modeling [68], [69], [70], and better boundary delineation [71], [72], [73], [74].”
- SAM-Adapter: Adapting Segment Anything in Underperformed Scenes (2023, background): “…the remarkable advancements in deep-learning-based methods such as fully convolutional networks (FCN) [35], encoder-decoder structures [41, 50, 14, 1, 29], dilated convolutions [3, 4, 5, 6, 34], pyramid structures [60, 5, 52, 6, 57], attention modules [51, 16, 62], and transformers [54, 48, 45, 8].”