Danpei Zhao

Danpei Zhao

orcid

Research Focus & Metrics

Academic Career Length

20Years (2007-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
7 May 2019 in Remote Sensing
Verified
Journal Article
Open access
PDF file
ZLZiming Liu
Ziming Liu
DZDanpei Zhao
Danpei Zhao
ZSZhenwei Shi
Zhenwei Shi
ZJZhiguo Jiang
Zhiguo Jiang
Traditional oil tank detection methods often use geometric shape information. However, it is difficult to guarantee accurate detection under a variety of disturbance factors, especially various colors, scale differences, and the shadows caused by view angle and illumination. Therefore, we propose an unsupervised saliency model with Color Markov Chain (US-CMC) to deal with oil tank detection. To avoid the influence of shadows, we make use of the CIE Lab space to construct a Color Markov Chain and generate a bottom-up latent saliency map. Moreover, we build a circular feature map based on a radial symmetric circle, which makes true targets to be strengthened for a subjective detection task. Besides, we combine the latent saliency map with the circular feature map, which can effectively suppress other salient regions except for oil tanks. Extensive experimental results demonstrate that it outperforms 15 saliency models for remote sensing images (RSIs). Compared with conventional oil tank detection methods, US-CMC has achieved better results and is also more robust for view angle, shadow, and shape similarity problems.

21 August 2024 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
BYBo Yuan
Bo Yuan
DZDanpei Zhao
Danpei Zhao
Continual learning, also known as incremental learning or life-long learning, stands at the forefront of deep learning and AI systems. It breaks through the obstacle of one-way training on close sets and enables continuous adaptive learning on open-set conditions. In the recent decade, continual learning has been explored and applied in multiple fields especially in computer vision covering classification, detection and segmentation tasks. Continual semantic segmentation (CSS), of which the dense prediction peculiarity makes it a challenging, intricate and burgeoning task. In this paper, we present a review of CSS, committing to building a comprehensive survey on problem formulations, primary challenges, universal datasets, neoteric theories and multifarious applications. Concretely, we begin by elucidating the problem definitions and primary challenges. Based on an in-depth investigation of relevant approaches, we sort out and categorize current CSS models into two main branches including data-replay and data-free sets. In each branch, the corresponding approaches are similarity-based clustered and thoroughly analyzed, following qualitative comparison and quantitative reproductions on relevant datasets. Besides, we also introduce four CSS specialities with diverse application scenarios and development tendencies. Furthermore, we develop a benchmark for CSS encompassing representative references, evaluation results and reproductions. We hope this survey can serve as a reference-worthy and stimulating contribution to the advancement of the life-long learning field, while also providing valuable perspectives for related fields.

15 December 2023 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
WLWentao Li
Wentao Li
DZDanpei Zhao
Danpei Zhao
BYBo Yuan
Bo Yuan
YGYue Gao
Yue Gao
ZSZhenwei Shi
Zhenwei Shi
Fine-grained object detection (FGOD) extends object detection with the capability of fine-grained recognition. In recent two-stage FGOD methods, the region proposal serves as a crucial link between detection and fine-grained recognition. However, current methods overlook that some proposal-related procedures inherited from general detection are not equally suitable for FGOD, limiting the multi-task learning from generation, representation, to utilization. In this paper, we present PETDet (Proposal Enhancement for Two-stage fine-grained object detection) to better handle the sub-tasks in two-stage FGOD methods. Firstly, an anchor-free Quality Oriented Proposal Network (QOPN) is proposed with dynamic label assignment and attention-based decomposition to generate high-quality oriented proposals. Additionally, we present a Bilinear Channel Fusion Network (BCFN) to extract independent and discriminative features of the proposals. Furthermore, we design a novel Adaptive Recognition Loss (ARL) which offers guidance for the R-CNN head to focus on high-quality proposals. Extensive experiments validate the effectiveness of PETDet. Quantitative analysis reveals that PETDet with ResNet50 reaches state-of-the-art performance on various FGOD datasets, including FAIR1M-v1.0 (42.96 AP), FAIR1M-v2.0 (48.81 AP), MAR20 (85.91 AP) and ShipRSImageNet (74.90 AP). The proposed method also achieves superior compatibility between accuracy and inference speed. Our code and models will be released at https://github.com/canoe-Z/PETDet.

8 May 2023 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
DZDanpei Zhao
Danpei Zhao
BYBo Yuan
Bo Yuan
ZSZhenwei Shi
Zhenwei Shi
As a front-burner problem in incremental learning, class incremental semantic segmentation (CISS) is plagued by catastrophic forgetting and semantic drift. Although recent methods have utilized knowledge distillation to transfer knowledge from the old model, they are still unable to avoid pixel confusion, which results in severe misclassification after incremental steps due to the lack of annotations for past and future classes. Meanwhile data-replay-based approaches suffer from storage burdens and privacy concerns. In this paper, we propose to address CISS without exemplar memory and resolve catastrophic forgetting as well as semantic drift synchronously. We present Inherit with Distillation and Evolve with Contrast (IDEC), which consists of a Dense Knowledge Distillation on all Aspects (DADA) manner and an Asymmetric Region- wise Contrastive Learning (ARCL) module. Driven by the devised dynamic class-specific pseudo-labelling strategy, DADA distils intermediate-layer features and output-logits collaboratively with more emphasis on semantic-invariant knowledge inheritance. ARCL implements region- wise contrastive learning in the latent space to resolve semantic drift among known classes, current classes, and unknown classes. We demonstrate the effectiveness of our method on multiple CISS tasks by state-of-the-art performance, including Pascal VOC 2012, ADE20 K and ISPRS datasets. Our method also shows superior anti-forgetting ability, particularly in multi-step CISS tasks.

25 February 2021 in Remote Sensing
Verified
Journal Article
Open access
PDF file
ZYZhichao Yuan
Zhichao Yuan
ZLZiming Liu
Ziming Liu
CZChunbo Zhu
Chunbo Zhu
BYBo Yuan
Bo Yuan
DZDanpei Zhao
Danpei Zhao
Object detection in optical remote sensing images (ORSIs) remains a difficult task because ORSIs always have some specific characteristics such as scale-differences between classes, numerous instances in one image and complex background texture. To address these problems, we propose a new Multi-Feature Pyramid Network (MFPNet) with Receptive Field Block (RFB) that integrates both local and global features to detect scattered objects and targets with scale-differences in ORSIs. We build a Multi-Feature Pyramid Module (M-FPM) with two cascaded convolution pyramids as the main structure of MFPNet, which handles object detection of different scales very well. RFB is designed to construct local context information, which makes the network more suitable for the objects detection around complex background. Asymmetric convolution kernel is introduced to RFB to improve the ability of feature attraction by adding nonlinear transformation. Then, a two-step detection network is constructed to combine the M-FPM and RFB to obtain more accurate results. Through a comprehensive evaluation of the experimental results on two publicly available remote sensing datasets Levir and DIOR, we demonstrate that our method outperforms state-of-the-art networks for about 1.3% mAP in Levir dataset and 4.1% mAP in DIOR dataset. Experimental results prove the effectiveness of our method in ORSIs of complex environments.

21 November 2017 in Remote Sensing
Verified
Journal Article
Open access
PDF file
BCBowen Cai
Bowen Cai
ZJZhiguo Jiang
Zhiguo Jiang
Haopeng ZhangHaopeng Zhang
Haopeng Zhang
DZDanpei Zhao
Danpei Zhao
YYYuan Yao
Yuan Yao
Deep convolutional neural network (CNN) achieves outstanding performance in the field of target detection. As one of the most typical targets in remote sensing images (RSIs), airport has attracted increasing attention in recent years. However, the essential challenge for using deep CNN to detect airport is the great imbalance between the number of airports and background examples in large-scale RSIs, which may lead to over-fitting. In this paper, we develop a hard example mining and weight-balanced strategy to construct a novel end-to-end convolutional neural network for airport detection. The initial motivation of the proposed method is that backgrounds contain an overwhelming number of easy examples and a few hard examples. Therefore, we design a hard example mining layer to automatically select hard examples by their losses, and implement a new weight-balanced loss function to optimize CNN. Meanwhile, the cascade design of proposal extraction and object detection in our network releases the constraint on input image size and reduces spurious false positives. Compared with geometric characteristics and low-level manually designed features, the hard example mining based network could extract high-level features, which is more robust for airport detection in complex environment. The proposed method is validated on a multi-scale dataset with complex background collected from Google Earth. The experimental results demonstrate that our proposed method is robust, and superior to the state-of-the-art airport detection models.