Combining Faster R-CNN and Model-Driven Clustering for Elongated Object Detection

Fang, Fen; Li, Liyuan; Zhu, Hongyuan; Lim, Joo‐Hwee

doi:10.1109/tip.2019.2947792

Cited by 63 publications

(19 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In past few years, deep convoultional neural networks have made great progress in 2D object detection [11], [36], [24], [35]. The object detection methods mainly consist of twostage approaches [11], [21], [2], [20], [56] and one-stage approaches [24], [3], [51], [23], [22]. The two-stage approaches first extract some candidate class-agnostic proposals and second classify these proposals into specific classes, while the one-stage approaches directly predict class-ware boundingboxes.…”

Section: Related Work a 2d Object Detectionmentioning

confidence: 99%

Shape Prior Non-Uniform Sampling Guided Real-time Stereo 3D Object Detection

Gao,

Cao,

Pang

2021

Preprint

View full text Add to dashboard Cite

Pseudo-LiDAR based 3D object detectors have gained popularity due to their high accuracy. However, these methods need dense depth supervision and suffer from inferior speed. To solve these two issues, a recently introduced RTS3D builds an efficient 4D Feature-Consistency Embedding (FCE) space for the intermediate representation of object without depth supervision. FCE space splits the entire object region into 3D uniform grid latent space for feature sampling point generation, which ignores the importance of different object regions. However, we argue that, compared with the inner region, the outer region plays a more important role for accurate 3D detection. To encode more information from the outer region, we propose a shape prior non-uniform sampling strategy that performs dense sampling in outer region and sparse sampling in inner region. As a result, more points are sampled from the outer region and more useful features are extracted for 3D detection. Further, to enhance the feature discrimination of each sampling point, we propose a high-level semantic enhanced FCE module to exploit more contextual information and suppress noise better. Experiments on the KITTI dataset are performed to show the effectiveness of the proposed method. Compared with the baseline RTS3D, our proposed method has 2.57% improvement on AP 3d almost without extra network parameters. Moreover, our proposed method outperforms the state-of-the-art methods without extra supervision at a real-time speed.

show abstract

Section: Related Work a 2d Object Detectionmentioning

confidence: 99%

Shape Prior Non-Uniform Sampling Guided Real-time Stereo 3D Object Detection

Gao,

Cao,

Pang

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Our OLS can be easily applied to the object detection framework [66], [67], [68], [69], [70]. We select YOLO [65] as our basic detector.…”

Section: Object Detectionmentioning

confidence: 99%

Delving Deep into Label Smoothing

Zhang,

Jiang,

Hou

et al. 2020

Preprint

View full text Add to dashboard Cite

Label smoothing is an effective regularization tool for deep neural networks (DNNs), which generates soft labels by applying a weighted average between the uniform distribution and the hard label. It is often used to reduce the overfitting problem of training DNNs and further improve classification performance. In this paper, we aim to investigate how to generate more reliable soft labels. We present an Online Label Smoothing (OLS) strategy, which generates soft labels based on the statistics of the model prediction for the target category. The proposed OLS constructs a more reasonable probability distribution between the target categories and non-target categories to supervise DNNs. Experiments demonstrate that based on the same classification models, the proposed approach can effectively improve the classification performance on CIFAR-100, ImageNet, and fine-grained datasets. Additionally, the proposed method can significantly improve the robustness of DNN models to noisy labels compared to current label smoothing approaches. The code will be made publicly available.

show abstract

“…In recent years, deep learning has become an emerging research hot spot in the field of artificial intelligence [1]- [4]. The rapid development of deep learning technology and the improvement of computer hardware performance have enabled deep learning, especially convolutional neural network (CNN) [5]- [7], to be successfully applied to many important tasks, such as image classification [8], [9], target detection [10], [11], and semantic segmentation [12], [13]. In addition, due to its excellent performance, deep learning has been widely used in the remote sensing image fields, such as remote sensing image classification [14]- [18], change detection [19], [20], and ground object extraction [21], [22].…”

Section: Introductionmentioning

confidence: 99%

NFANet: A Novel Method for Weakly Supervised Water Extraction from High-Resolution Remote Sensing Imagery

Lu,

Fang,

et al. 2022

Preprint

View full text Add to dashboard Cite

The use of deep learning for water extraction requires precise pixel-level labels. However, it is very difficult to label high-resolution remote sensing images at the pixel level. Therefore, we study how to utilize point labels to extract water bodies and propose a novel method called the neighbor feature aggregation network (NFANet). Compared with pixellevel labels, point labels are much easier to obtain, but they will lose much information. In this paper, we take advantage of the similarity between the adjacent pixels of a local water-body, and propose a neighbor sampler to resample remote sensing images. Then, the sampled images are sent to the network for feature aggregation. In addition, we use an improved recursive training algorithm to further improve the extraction accuracy, making the water boundary more natural. Furthermore, our method utilizes neighboring features instead of global or local features to learn more representative features. The experimental results show that the proposed NFANet method not only outperforms other studied weakly supervised approaches, but also obtains similar results as the state-of-the-art ones.

show abstract

Combining Faster R-CNN and Model-Driven Clustering for Elongated Object Detection

Cited by 63 publications

References 35 publications

Shape Prior Non-Uniform Sampling Guided Real-time Stereo 3D Object Detection

Shape Prior Non-Uniform Sampling Guided Real-time Stereo 3D Object Detection

Delving Deep into Label Smoothing

NFANet: A Novel Method for Weakly Supervised Water Extraction from High-Resolution Remote Sensing Imagery

Contact Info

Product

Resources

About