In this letter, we propose a conceptually simple and intuitive learning objective function, i.e., additive margin softmax, for face verification. In general, face verification tasks can be viewed as metric learning problems, even though lots of face verification models are trained in classification schemes. It is possible when a large-margin strategy is introduced into the classification model to encourage intraclass variance minimization. As one alternative, angular softmax has been proposed to incorporate the margin. In this letter, we introduce another kind of margin to the softmax loss function, which is more intuitive and interpretable. Experiments on LFW and MegaFace show that our algorithm performs better when the evaluation criteria are designed for very low false alarm rate.

Online Multi-Object Tracking (MOT) is a challenging problem and has many important applications including intelligence surveillance, robot navigation and autonomous driving. In existing MOT methods, individual object’s movements and inter-object relations are mostly modeled separately and relations between them are still manually tuned. In addition, inter-object relations are mostly modeled in a symmetric way, which we argue is not an optimal setting. To tackle those difficulties, in this paper, we propose a Deep Continuous Conditional Random Field (DCCRF) for solving the online MOT problem in a track-bydetection framework. The DCCRF consists of unary and pairwise terms. The unary terms estimate tracked objects’ displacements across time based on visual appearance information. They are modeled as deep Convolution Neural Networks, which are able to learn discriminative visual features for tracklet association. The asymmetric pairwise terms model inter-object relations in an asymmetric way, which encourages high-confidence tracklets to help correct errors of low-confidence tracklets and not to be affected by low-confidence ones much. The DCCRF is trained in an end-to-end manner for better adapting the influences of visual information as well as inter-object relations. Extensive experimental comparisons with state-of-the-arts as well as detailed component analysis of our proposed DCCRF on two public benchmarks demonstrate the effectiveness of our proposed MOT framework.

Semantic segmentation for unmanned aerial vehicle (UAV) remote sensing images has become one of the research focuses in the field of remote sensing at present, which could accurately analyze the ground objects and their relationships. However, conventional semantic segmentation methods based on deep learning require large-scale models that are not suitable for resource-constrained UAV remote sensing tasks. Therefore, it is important to construct a light-weight semantic segmentation method for UAV remote sensing images. With this motivation, we propose a light-weight neural network model with fewer parameters to solve the problem of semantic segmentation of UAV remote sensing images. The network adopts an encoder-decoder architecture. In the encoder, we build a light-weight convolutional neural network model with fewer channels of each layer to reduce the number of model parameters. Then, feature maps of different scales from the encoder are concatenated together after resizing to carry out the multiscale fusion. Moreover, we employ two attention modules to capture the global semantic information from the context and the correlation among channels in UAV remote sensing images. In the decoder part, the model obtains predictions of each pixel through the softmax function. We conducted experiments on the ISPRS Vaihingen dataset, UAVid dataset, and UDD6 dataset to verify the effectiveness of the light-weight network. Our method obtains quality semantic segmentation results evaluated on UAV remote sensing datasets with only 9 M parameters the model owns, which is competitive among popular methods with the same level of parameters.

Pedestrian detection has achieved great improvements in recent years, while complex occlusion handling and high accurate localization are still the most important problems. To take advantage of the body-part semantic information and the contextual information for pedestrian detection, we propose the part and context network (PCN) in this work. PCN is composed of three branches: the basic branch, the part branch and the context branch. It specially utilizes two branches to detect the pedestrians through the body-part semantic information and the contextual information, respectively. In the part branch, the semantic information of body parts can communicate with each other via LSTM. In the context branch, we adopt a local competition mechanism (maxout) for adaptive context scale selection. By combining the outputs of all branches, we develop a strong complementary pedestrian detector with a lower miss rate and higher localization accuracy, especially for the occlusion pedestrian. The combination of the body-part semantic information and the contextual information in pedestrian detection is fully explored in this work. Comprehensive evaluations on three challenging pedestrian detection datasets (i.e. Caltech, INRIA and KITTI) well demonstrate the effectiveness of our proposed PCN.