Deep learning based remote sensing image scene classification methods are the current mainstream, and enough labeled samples are very important for their performance.Considering the fact that manual labeling of samples requires high labor and time cost, lots of methods have been proposed to automatically generate pseudo samples from real samples, however, existing methods can not directly sift the pseudo samples from the perspective of model training. To address this problem, a generating and sifting pseudo labeled samples scheme is proposed in this paper. First of all, the existing SinGAN is used to generate multiple groups of pseudo samples from the real samples. Afterwards, the proposed quantitative sifting measure which can evaluate both the authenticity and diversity from the perspective of model training is employed to select the best pseudo samples from the multiple generated pseudo samples. Finally, the selected pseudo samples and real samples are used to pretrain and finetune the deep scene classification network (DSCN) respectively. Moreover, the focal loss which is originally proposed for object detection is adopted to replace the traditional cross entropy loss in this paper. A designed quantitative evaluation shows that the value of proposed quantitative sifting measure is proportional to the overall accuracy, which validates the effectiveness of proposed quantitative sifting measure. The comprehensive quantitative comparisons on AID and NWPU-RESISC45 datasets in terms of overall accuracy and confusion matrices demonstrate that incorporating the pseudo samples selected by proposed sifting measure and the focal loss can improve the performance of DSCN.

Modern deep-learning-based lane detection methods are successful in most scenarios but struggling for lane lines with complex topologies. In this work, we propose Cond-LaneNet, a novel top-to-down lane detection framework that detects the lane instances first and then dynamically predicts the line shape for each instance. Aiming to resolve lane instance-level discrimination problem, we introduce a conditional lane detection strategy based on conditional convolution and row-wise formulation. Further, we design the Recurrent Instance Module(RIM) to overcome the problem of detecting lane lines with complex topologies such as dense lines and fork lines. Benefit from the end-to-end pipeline which requires little post-process, our method has real-time efficiency. We extensively evaluate our method on three benchmarks of lane detection. Results show that our method achieves state-of-the-art performance on all three benchmark datasets. Moreover, our method has the coexistence of accuracy and efficiency, e.g. a 78.14 F1 score and 220 FPS on CULane.

No abstract

No abstract