Yiran Yang’s research while affiliated with Academy of Chinese Culture and Health Sciences and other places

Weakly Supervised 3D Object Detection (WS3DOD) aims to perform 3D object detection with little reliance on 3D labels, which greatly reduces the cost of 3D annotations. In recent literature, the pseudo-label-based approach brings impressive performance, which generates 3D pseudo-labels from 2D bounding boxes. Despite their success, two key issues remain unresolved that reduce the quality of 3D pseudo-labels: 1) the existing local object locating algorithm can not capture complete clusters of points globally, and 2) the existing algorithm can not capture sparse points caused by the unevenly distributed points obtained by LiDAR cameras. Hence, we propose GAL, a Graph-induced Adaptive Learning algorithm, to generate 3D pseudo-labels. First, we propose the Cluster Locating algorithm based on the Minimum Spanning Tree (MST) to globally locate the objects, which can leverage the characteristic that points inside an object are compact while points between objects are discrete. Second, we propose a density-guided adaptive learning algorithm to optimise the Cluster Locating algorithm, named Cuboid Drift. Cuboid Drift considers the inhomogeneous distribution of reflected points on different reflective surfaces of LiDAR imaging. Finally, 3D pseudo-labels generated by GAL are leveraged to train 3D detectors. Extensive experiments on the challenging KITTI and DAIR-V2X-V dataset demonstrate that GAL without 3D labels can be comparable with strongly supervised approaches and outperforms the previous state-of-the-art WS3DOD methods. Moreover, our method saves 88% of the time spent on pseudo-label generation.

With the advancement of global civilisation, monitoring and managing dumpsites have become essential parts of environmental governance in various countries. Dumpsite locations are difficult to obtain in a timely manner by local government agencies and environmental groups. The World Bank shows that governments need to spend massive labour and economic costs to collect illegal dumpsites to implement management. Here we show that applying novel deep convolutional networks to high-resolution satellite images can provide an effective, efficient, and low-cost method to detect dumpsites. In sampled areas of 28 cities around the world, our model detects nearly 1000 dumpsites that appeared around 2021. This approach reduces the investigation time by more than 96.8% compared with the manual method. With this novel and powerful methodology, it is now capable of analysing the relationship between dumpsites and various social attributes on a global scale, temporally and spatially.

Continual learning is an effective way to overcome catastrophic forgetting (CF) in incremental learning for semantic segmentation. The existing continual semantic segmentation (CSS) methods of remote sensing (RS) ignore the semantic relationships among pixels across different images, which will lead to disappointing segmentation results, such as edge pixel misclassification and small object omission. In this article, we propose a framework for modeling cross-image semantic relationship dependencies (MiCro), which aims to learn an interclass separable and intraclass cohesive feature space from the pixel relationships across various images to ensure that learned categories can prevent CF in the incremental process. Specifically, we exploit the relationships among pixels of images in minibatch to construct three losses: 1) cross-image feature relationship distillation (CFRD) loss, which builds a well-structured feature space; 2) cross-image intraclass feature cohesion (CIFC) loss, which is devised to make intraclass features more cohesive; and 3) cross-image class-area weighted cross-entropy (CCWCE) loss, which is mainly employed to inversely weight the proportion of category area in minibatch. The effectiveness of the proposed approach is demonstrated by extensive experiments on three RS semantic segmentation datasets from ISPRS Vaihingen, ISPRS Potsdam, and iSAID. MiCro is superior to the current most advanced methods in most incremental settings, especially improving mIoU by 11.59% on ISPRS Vaihingen, 13.17% on ISPRS Potsdam, and 15.01% on iSAID in the most difficult incremental settings, which promotes the CSS to a state-of-the-art (SOTA) level. The code will be available at https://github.com/RongXueE/MiCro .

Cloud detection relying on deep convolutional neural networks (DCNNs) obtains remarkable accuracy gains at the expense of high computation and storage costs, which are difficult to deploy to resource-constrained devices, such as intelligent satellites. Recently, knowledge distillation (KD) has been a promising solution for a compact model. However, most existing KD methods only transfer the feature relationship of pairwise pixel, which fails to cope with thin clouds and cloud-like objects in complex scenes. Furthermore, those KD methods directly imitate the output of the complicated model regardless of the correctness. In this article, we propose a novel category correlation and adaptive KD (CAKD) framework for the lightweight cloud detection network. We design a category relational context (CRC) module to refine the structured pixel-category correlation from the teacher and student network. Then, we perform the category correlation distillation (CCD) to make the student model better address the intraclass consistency and the interclass difference, thus reducing the category confusion. Besides, a pixel-adaptive distillation (PAD) module is utilized to adaptively transfer the soft-output knowledge of a teacher model by extracting the teacher’s pixel prediction probability. Extensive experiments on Landsat 8, Landsat 7, Gaofen-2, Gaofen-1, and Google Earth dataset report the effectiveness and universality of our distillation method. The CAKD allows MobileNetV2 with 2.31M parameters and 4.63G float-point operations (FLOPs) to outperform advanced cloud detection methods without the added inference overhead.

Lightweight object detector is currently gaining more and more popularity in remote sensing. In general, it is hard for lightweight detectors to achieve competitive performance compared with the traditional deep models, while knowledge distillation (KD) is a promising training method to tackle the issue. Since the background is more complicated and the object size varies extremely in remote sensing images, it will deliver lots of noise and affect the training performance when directly applying the existing KD methods. To tackle the above problems, we propose an adaptive reinforcement supervision distillation (ARSD) framework to promote the detection capability of the lightweight model. First, we put forward a multiscale core features imitation (MCFI) module for transferring the knowledge of features, which can adaptively select the multiscale core features of objects for distillation and focus more on the features of small objects by an area-weighted strategy. In addition, a strict supervision regression distillation (SSRD) module is designed to select the optimal regression results for distillation, which facilitates the student to effectively imitate the more precise regression output of the teacher network. Massive experiments on a large-scale Dataset for Object deTection in Aerial images (DOTA), object DetectIon in Optical Remote sensing images (DIOR), and Northwestern Polytechnical University Very-High-Resolution 10-class (NWPU VHR) datasets prove that ARSD outperforms the existing distillation state-of-the-art (SOTA) methods. Moreover, the performance of the lightweight model trained with our method transcends other classic heavy and lightweight detectors, which beneficiates the development of lightweight models.

The label assignment problem is a core task in object detection, which mainly focuses on how to define the positive/negative samples during the training phase. Recent works have proved that label assignment is significant for performance improvement of the detector. In this paper, we propose an exquisite strategy that can dynamically assign labels according samples' joint scores (classification and location). Moreover, our strategy can apply to both 2D and 3D monocular detectors. In our strategy, we formulate label assignment as an optimization problem. Concretely, we first calculate the classification and location costs of each sample, which are treated as points in a two-dimensional coordinate system. Then an optimal divider line that minimizes the sum of point-to-line distances is designed to separate the positive/negative samples. An iterative Genetic Algorithm is employed in acquiring the optimal solution. Furthermore, a GIoU auxiliary branch is devised to keep sample selection consistent during the training and testing phase. Benefitting from the non-maximum suppression (NMS) that utilizes the joint scores of classification and location, excellent detection performance is achieved. Extensive experiments conducted on MS COCO, PASCAL VOC (2D object detection), and KITTI (3D object detection) verify the effectiveness and universality of our proposed Optimal Partition Assignment (OPA).

In recent years, more concerns are shed on the lightweight detection model in remote sensing (RS), but it is difficult to reach a competitive performance relative to the deep model. Knowledge distillation has been verified as a promising method, which can promote the performance of the lightweight model without extra parameters. While there are two key issues of detection distillation, one is the sample selection and the other is the knowledge selection. Since the varying object size and complex features in RS, the existing methods based on the fixed threshold are incapable of selecting the optimal distillation samples and they also ignore the potential multivariate knowledge among RS samples simultaneously. In this article, we propose a statistical sample selection and multivariate knowledge mining framework. The statistical sample selection module formulates the task as the modeling and splitting of the probability distribution of sample selection cost, which is more suitable for dynamically choosing multiscale samples in RS and eliminates the distortion of previous static distillation selection. Furthermore, to mine the complex feature knowledge of samples in RS, we design a multivariate knowledge mining module, in which knowledge includes explicit and implicit knowledge. The proposed module validly delivers the core knowledge from the teacher model to the lightweight model. Massive experiments on three challenging RS datasets [a large-scale Dataset for Object deTection in Aerial images (DOTA), Northwestern Polytechnical University very-high-resolution 10-class (NWPU VHR-10), and object DetectIon in Optical Remote sensing images (DIOR)] prove that our method achieves state-of-the-art performance.