SSPNet: Scale Selection Pyramid Network for Tiny Person Detection From UAV Images

Hong, Mingbo; Li, Shuiwang; Yang, Yuchao; Zhu, Feiyu; Zhao, Qijun; Lü, Li

doi:10.1109/lgrs.2021.3103069

Cited by 40 publications

(28 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Despite its success and popularity, the basic interaction design is not perfect due to the inherent scale-level inconsistencies that basic up-sampling and fusion cannot deal with [74]. Observing this, the following approaches aim to refine the features emanated from different stages of the backbone trunk in a proper fashion [86], or optimize the fusion process by dynamically controlling the information flow between different layers [87], [88]. Woo et al [86] proposed StairNet where deconvolution was exploited to enlarge the feature map, such learning-based up-sampling function can achieve a more refined feature than naïve kernel-based up-sampling and allows that the information of different pyramid levels propagates more efficiently [89].…”

Section: Feature-fusion Methodsmentioning

confidence: 99%

Towards Large-Scale Small Object Detection: Survey and Benchmarks

Chen¹,

Yuan²,

Yao³

et al. 2022

Preprint

View full text Add to dashboard Cite

With the rise of deep convolutional neural networks, object detection has achieved prominent advances in past years. However, such prosperity could not camouflage the unsatisfactory situation of Small Object Detection (SOD), one of the notoriously challenging tasks in computer vision, owing to the poor visual appearance and noisy representation caused by the intrinsic structure of small targets. In addition, large-scale dataset for benchmarking small object detection methods remains a bottleneck. In this paper, we first conduct a thorough review of small object detection. Then, to catalyze the development of SOD, we construct two large-scale Small Object Detection dAtasets (SODA), SODA-D and SODA-A, which focus on the Driving and Aerial scenarios respectively. SODA-D includes 24704 high-quality traffic images and 277596 instances of 9 categories. For SODA-A, we harvest 2510 high-resolution aerial images and annotate 800203 instances over 9 classes. The proposed datasets, as we know, are the first-ever attempt to large-scale benchmarks with a vast collection of exhaustively annotated instances tailored for multi-category SOD. Finally, we evaluate the performance of mainstream methods on SODA. We expect the released benchmarks could facilitate the development of SOD and spawn more breakthroughs in this field. Datasets and codes will be available soon at: https://shaunyuan22.github.io/SODA.

show abstract

Section: Feature-fusion Methodsmentioning

confidence: 99%

Towards Large-Scale Small Object Detection: Survey and Benchmarks

Chen¹,

Yuan²,

Yao³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Nguyen et al [26] propose a detection method based on capsule network [30]. Li et al [20] propose that the artifacts in affine face warping as the distinctive feature to forgery detect, and achieve state-of-the-art performance based on SSPNet [16]. Li et al [19] propose Face X-ray that focuses on the blending step of forgery and achieve state-of-the-art transferability performance.…”

Section: Related Workmentioning

confidence: 99%

Block shuffling learning for Deepfake Detection

Liu¹,

Lian²,

Gu³

et al. 2022

Preprint

View full text Add to dashboard Cite

Although the deepfake detection based on convolutional neural network has achieved good results, the detection results show that these detectors show obvious performance degradation when the input images undergo some common transformations (like resizing, blurring), which indicates that the generalization ability of the detector is insufficient. In this paper, we propose a novel block shuffling learning method to solve this problem. Specifically, we divide the images into blocks and then introduce the random shuffling to intra-block and inter-block. Intra-block shuffling increases the robustness of the detector and we also propose an adversarial loss algorithm to overcome the over-fitting problem brought by the noise introduced by shuffling. Moreover, we encourage the detector to focus on finding differences among the local features through inter-block shuffling, and reconstruct the spatial layout of the blocks to model the semantic associations between them. Especially, our method can be easily integrated with various CNN models. Extensive experiments show that our proposed method achieves state-of-the-art performance in forgery face detection, including good generalization ability in the face of common image transformations.

show abstract

“…In addition, FPN pays more attention to the feature fusion of adjacent layers. When there is a certain span between the low-level feature map and the high-level feature map fusion, the location information is not necessarily accurate, and its features will be weakened during the fusion [ 25 ].…”

Section: Improved Network Algorithm Based On Faster Rcnn-fpnmentioning

confidence: 99%

Tire Speckle Interference Bubble Defect Detection Based on Improved Faster RCNN-FPN

Yang

Jiao

Wang

et al. 2022

Sensors

View full text Add to dashboard Cite

With the development of neural networks, object detection based on deep learning is developing rapidly, and its applications are gradually increasing. In the tire industry, detecting speckle interference bubble defects of tire crown has difficulties such as low image contrast, small object scale, and large internal differences of defects, which affect the detection precision. To solve these problems, we propose a new feature pyramid network based on Faster RCNN-FPN. It can fuse features across levels and directions to improve small object detection and localization, and increase object detection precision. The method has proven its effectiveness through cross-validation experiments. On a tire crown bubble defect dataset, the mAP [0.5:0.95] increased by 2.08% and the AP0.5 increased by 2.4% over the original network. The results show that the improved network significantly improves detecting tire crown bubble defects.

show abstract

SSPNet: Scale Selection Pyramid Network for Tiny Person Detection From UAV Images

Cited by 40 publications

References 23 publications

Towards Large-Scale Small Object Detection: Survey and Benchmarks

Towards Large-Scale Small Object Detection: Survey and Benchmarks

Block shuffling learning for Deepfake Detection

Tire Speckle Interference Bubble Defect Detection Based on Improved Faster RCNN-FPN

Contact Info

Product

Resources

About