• Publications
  • Influence
Deep High-Resolution Representation Learning for Human Pose Estimation
TLDR
This paper proposes a network that maintains high-resolution representations through the whole process of human pose estimation and empirically demonstrates the effectiveness of the network through the superior pose estimation results over two benchmark datasets: the COCO keypoint detection dataset and the MPII Human Pose dataset. Expand
Deep High-Resolution Representation Learning for Visual Recognition
TLDR
The superiority of the proposed HRNet in a wide range of applications, including human pose estimation, semantic segmentation, and object detection, is shown, suggesting that the HRNet is a stronger backbone for computer vision problems. Expand
High-Resolution Representations for Labeling Pixels and Regions
TLDR
A simple modification is introduced to augment the high-resolution representation by aggregating the (upsampled) representations from all the parallel convolutions rather than only the representation from thehigh-resolution convolution, which leads to stronger representations, evidenced by superior results. Expand
Multi-Stage Self-Supervised Learning for Graph Convolutional Networks
TLDR
A novel training algorithm for Graph Convolutional Network, called Multi-Stage Self-Supervised (M3S) Training Algorithm, combined with self-supervised learning approach, focusing on improving the generalization performance of GCNs on graphs with few labeled nodes. Expand
Deep Feature Consistent Variational Autoencoder
TLDR
This work employs a pre-trained deep convolutional neural network and uses its hidden features to define a feature perceptual loss for VAE training, which ensures the VAE's output to preserve the spatial correlation characteristics of the input, thus leading the output to have a more natural visual appearance and better perceptual quality. Expand
IGCV3: Interleaved Low-Rank Group Convolutions for Efficient Deep Neural Networks
TLDR
It is empirically demonstrate that the combination of low-rank and sparse kernels boosts the performance and the superiority of the proposed approach to the state-of-the-arts, IGCV2 and MobileNetV2 over image classification on CIFAR and ImageNet and object detection on COCO. Expand
AdaGCN: Adaboosting Graph Convolutional Networks into Deep Models
TLDR
A novel RNN-like deep graph neural network architecture by incorporating AdaBoost into the computation of network called AdaGCN~(AdaBoosting Graph Convolutional Network) has the ability to efficiently extract knowledge from high-order neighbors and integrate knowledge from different hops of neighbors into the network in an AdaBoost way. Expand
Virtual Adversarial Training on Graph Convolutional Networks in Node Classification
TLDR
Virtual Adversarial Training (VAT), an adversarial regularization method based on both labeled and unlabeled data, is applied on the supervised loss of GCN to enhance its generalization performance and yields improvement on the Symmetrical Laplacian Smoothness of GCNs. Expand
Enhancing the Robustness of Deep Neural Networks by Boundary Conditional GAN
TLDR
This work proposes a novel defense mechanism called Boundary Conditional GAN to enhance the robustness of deep neural networks against adversarial examples and empirically shows that the model improved by the approach consistently defenses against various types of adversarial attacks successfully. Expand
Human Pose Estimation Using Global and Local Normalization
TLDR
A two-stage normalization scheme, human body normalization and limb normalization, is presented to make the distribution of the relative joint locations compact, resulting in easier learning of convolutional spatial models and more accurate pose estimation. Expand
...
1
2
3
4
5
...