Yang Zhao

TL;DR: 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.

TL;DR: The High-Resolution Network (HRNet) as mentioned in this paper maintains high-resolution representations through the whole process by connecting the high-to-low resolution convolution streams in parallel and repeatedly exchanging the information across resolutions.

TL;DR: 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.

TL;DR: An effective lightweight model, namely Mobile Face Alignment Network (MobileFAN), using a simple backbone MobileNetV2 as the encoder and three deconvolutional layers as the decoder is proposed, which achieves superior or equivalent performance compared with state-of-the-art models.

TL;DR: Experimental results of the proposed novel random mask covariance network (MaskCOV), which integrates an auxiliary self-supervised learning module with a powerful in-image data augmentation scheme for the ultra-FGVC, demonstrate its superiority and potential of MaskCOV concept, which pushes research boundary forward from the fine-grained to theUltra-fine-Grained visual categorization.