2020/10/26 by Luanxuan Hou, Hou, Luanxuan, Jie Cao +9
Computer Science · #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Human Pose and Action Recognition #Image and Object Detection Techniques #cs.CV
paper · pdf · doi:10.48550/arxiv.2010.14076
Accepted by ICPR2020. arXiv admin note: text overlap with arXiv:2003.07516
arxiv created 2020/10/26 · openalex publication_date 2020/10/26 · arxiv updated 2020/10/28 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
We propose an augmented Parallel-Pyramid Net (P2~Net) with feature refinement by dilated bottleneck and attention module. During data preprocessing, we proposed a differentiable auto data augmentation (DA2) method. We formulate the problem of searching data augmentaion policy in a differentiable form, so that the optimal policy setting can be easily updated by back propagation during training. DA2 improves the training efficiency. A parallel-pyramid structure is followed to compensate the information loss introduced by the network. We innovate two fusion structures, i.e. Parallel Fusion and Progressive Fusion, to process pyramid features from backbone network. Both fusion structures leverage the advantages of spatial information affluence at high resolution and semantic comprehension at low resolution effectively. We propose a refinement stage for the pyramid features to further boost the accuracy of our network. By introducing dilated bottleneck and attention module, we increase the receptive field for the features with limited complexity and tune the importance to different feature channels. To further refine the feature maps after completion of feature extraction stage, an Attention Module (AM) is defined to extract weighted features from different scale feature maps generated by the parallel-pyramid structure. Compared with the traditional up-sampling refining, AM can better capture the relationship between channels. Experiments corroborate the effectiveness of our proposed method. Notably, our method achieves the best performance on the challenging MSCOCO and MPII datasets.