Pyramid Scene Parsing Network
- Hengshuang Zhao, Jianping Shi, Xiaojuan Qi, Xiaogang Wang, Jiaya Jia
- Computer ScienceComputer Vision and Pattern Recognition
- 4 December 2016
This paper exploits the capability of global context information by different-region-based context aggregation through the pyramid pooling module together with the proposed pyramid scene parsing network (PSPNet) to produce good quality results on the scene parsing task.
Hierarchical Saliency Detection
- Qiong Yan, Li Xu, Jianping Shi, Jiaya Jia
- Environmental ScienceIEEE Conference on Computer Vision and Pattern…
- 23 June 2013
This work tackles saliency detection from a scale point of view and proposes a multi-layer approach to analyze saliency cues, by finding saliency values optimally in a tree model.
Path Aggregation Network for Instance Segmentation
- Shu Liu, Lu Qi, Haifang Qin, Jianping Shi, Jiaya Jia
- Computer ScienceIEEE/CVF Conference on Computer Vision and…
- 5 March 2018
Path Aggregation Network (PANet) is proposed aiming at boosting information flow in proposal-based instance segmentation framework by enhancing the entire feature hierarchy with accurate localization signals in lower layers by bottom-up path augmentation.
Abnormal Event Detection at 150 FPS in MATLAB
- Cewu Lu, Jianping Shi, Jiaya Jia
- Computer ScienceIEEE International Conference on Computer Vision
- 1 December 2013
An efficient sparse combination learning framework based on inherent redundancy of video structures achieves decent performance in the detection phase without compromising result quality and reaches high detection rates on benchmark datasets at a speed of 140-150 frames per second on average.
ICNet for Real-Time Semantic Segmentation on High-Resolution Images
- Hengshuang Zhao, Xiaojuan Qi, Xiaoyong Shen, Jianping Shi, Jiaya Jia
- Computer ScienceEuropean Conference on Computer Vision
- 27 April 2017
An image cascade network (ICNet) that incorporates multi-resolution branches under proper label guidance to address the challenging task of real-time semantic segmentation is proposed and in-depth analysis of the framework is provided.
Libra R-CNN: Towards Balanced Learning for Object Detection
- Jiangmiao Pang, Kai Chen, Jianping Shi, H. Feng, Wanli Ouyang, Dahua Lin
- Computer ScienceComputer Vision and Pattern Recognition
- 4 April 2019
Libra R-CNN is proposed, a simple but effective framework towards balanced learning for object detection that integrates three novel components: IoU-balanced sampling, balanced feature pyramid, and balanced L1 loss, respectively for reducing the imbalance at sample, feature, and objective level.
Hybrid Task Cascade for Instance Segmentation
- Kai Chen, Jiangmiao Pang, Dahua Lin
- Computer ScienceComputer Vision and Pattern Recognition
- 22 January 2019
This work proposes a new framework, Hybrid Task Cascade (HTC), which differs in two important aspects: (1) instead of performing cascaded refinement on these two tasks separately, it interweaves them for a joint multi-stage processing; (2) it adopts a fully convolutional branch to provide spatial context, which can help distinguishing hard foreground from cluttered background.
Spatial As Deep: Spatial CNN for Traffic Scene Understanding
- Xingang Pan, Jianping Shi, Ping Luo, Xiaogang Wang, Xiaoou Tang
- Computer ScienceAAAI Conference on Artificial Intelligence
- 17 December 2017
This paper proposes Spatial CNN (SCNN), which generalizes traditional deep layer- by-layer convolutions to slice-by-slice convolutions within feature maps, thus enabling message passings between pixels across rows and columns in a layer.
PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection
- Shaoshuai Shi, Chaoxu Guo, Hongsheng Li
- Computer ScienceComputer Vision and Pattern Recognition
- 31 December 2019
The proposed PV-RCNN surpasses state-of-the-art 3D detection methods with remarkable margins and deeply integrates both 3D voxel Convolutional Neural Network and PointNet-based set abstraction to learn more discriminative point cloud features.
Context Encoding for Semantic Segmentation
- Hang Zhang, Kristin J. Dana, Amit Agrawal
- Computer ScienceIEEE/CVF Conference on Computer Vision and…
- 23 March 2018
The proposed Context Encoding Module significantly improves semantic segmentation results with only marginal extra computation cost over FCN, and can improve the feature representation of relatively shallow networks for the image classification on CIFAR-10 dataset.
...
...