A Novel Upsampling and Context Convolution for Image Semantic Segmentation

Semantic segmentation, which refers to pixel-wise classification of an image, is a fundamental topic in computer vision owing to its growing importance in robot vision and autonomous driving industries. It provides rich information about objects in the scene such as object boundary, category, and location. Recent methods for semantic segmentation often employ an encoder-decoder structure using deep convolutional neural networks. The encoder part extracts feature of the image using several filters and pooling operations, whereas the decoder part gradually recovers the low-resolution feature maps of the encoder into a full input resolution feature map for pixel-wise prediction. However, the encoder-decoder variants for semantic segmentation suffer from severe spatial information loss, caused by pooling operations or convolutions with stride, and does not consider the context in the scene. In this paper, we propose a dense upsampling convolution method based on guided filtering to effectively preserve the spatial information of the image in the network. We further propose a novel local context convolution method that not only covers larger-scale objects in the scene but covers them densely for precise object boundary delineation. Theoretical analyses and experimental results on several benchmark datasets verify the effectiveness of our method. Qualitatively, our approach delineates object boundaries at a level of accuracy that is beyond the current excellent methods. Quantitatively, we report a new record of 82.86% and 81.62% of pixel accuracy on ADE20K and Pascal-Context benchmark datasets, respectively. In comparison with the state-of-the-art methods, the proposed method offers promising improvements.

Person re-identification based on Res2Net network

Person re-identification (re-ID) has been gaining in popularity in the research community owing to its numerous applications and growing importance in the surveillance industry. Person re-ID remains challenging due to significant intra-class variations across different cameras. In this paper, we propose a multi-task network that simultaneously computes the identification loss and verification loss. Given a pair of input images, the network predicts the identities of the two input images and whether they belong to the same identity. In order to obtain deeper feature information of pedestrians, we propose to use the latest Res2Net network for feature extraction. Experiments on several large-scale person re-ID benchmark datasets demonstrate the accuracy of our approach. For example, rank-1 accuracies are 82.67% (+0.51) and 92.93% (+0.21) for the DukeMTMC and Market-1501 datasets, respectively. The proposed method shows encouraging improvements compared with state-of-the-art methods.