English
Related papers

Related papers: A Holistically-Guided Decoder for Deep Representat…

200 papers

Learning powerful feature representations for image retrieval has always been a challenging task in the field of remote sensing. Traditional methods focus on extracting low-level hand-crafted features which are not only time-consuming but…

Computer Vision and Pattern Recognition · Computer Science 2017-05-22 Weixun Zhou , Shawn Newsam , Congmin Li , Zhenfeng Shao

High resolution and advanced semantic representation are both vital for dense prediction. Empirically, low-resolution feature maps often achieve stronger semantic representation, and high-resolution feature maps generally can better…

Computer Vision and Pattern Recognition · Computer Science 2022-10-14 Jian Wang , Xiang Long , Guowei Chen , Zewu Wu , Zeyu Chen , Errui Ding

Point cloud classification plays an important role in a wide range of airborne light detection and ranging (LiDAR) applications, such as topographic mapping, forest monitoring, power line detection, and road detection. However, due to the…

Computer Vision and Pattern Recognition · Computer Science 2020-04-21 Congcong Wen , Lina Yang , Ling Peng , Xiang Li , Tianhe Chi

This paper proposes an innovative object detector by leveraging deep features learned in high-level layers. Compared with features produced in earlier layers, the deep features are better at expressing semantic and contextual information.…

Computer Vision and Pattern Recognition · Computer Science 2019-12-11 Wenchi Ma , Yuanwei Wu , Feng Cen , Guanghui Wang

Recent progress of deep image classification models has provided great potential to improve state-of-the-art performance in related computer vision tasks. However, the transition to semantic segmentation is hampered by strict memory…

Computer Vision and Pattern Recognition · Computer Science 2019-05-15 Ivan Krešo , Josip Krapac , Siniša Šegvić

Deep learning based methods, such as Convolution Neural Network (CNN), have demonstrated their efficiency in hyperspectral image (HSI) classification. These methods can automatically learn spectral-spatial discriminative features within…

Computer Vision and Pattern Recognition · Computer Science 2021-07-07 Yu Shen , Sijie Zhu , Chen Chen , Qian Du , Liang Xiao , Jianyu Chen , Delu Pan

Semantic segmentation is critical to image content understanding and object localization. Recent development in fully-convolutional neural network (FCN) has enabled accurate pixel-level labeling. One issue in previous works is that the FCN…

Computer Vision and Pattern Recognition · Computer Science 2016-07-08 Qin Huang , Chunyang Xia , Wenchao Zheng , Yuhang Song , Hao Xu , C. -C. Jay Kuo

One of the most common tasks in medical imaging is semantic segmentation. Achieving this segmentation automatically has been an active area of research, but the task has been proven very challenging due to the large variation of anatomy…

Computer Vision and Pattern Recognition · Computer Science 2018-04-10 Holger R. Roth , Chen Shen , Hirohisa Oda , Masahiro Oda , Yuichiro Hayashi , Kazunari Misawa , Kensaku Mori

The encoder-decoder architecture is widely used as a lightweight semantic segmentation network. However, it struggles with a limited performance compared to a well-designed Dilated-FCN model for two major problems. First, commonly used…

Computer Vision and Pattern Recognition · Computer Science 2022-05-11 Jiangyun Li , Sen Zha , Chen Chen , Meng Ding , Tianxiang Zhang , Hong Yu

Existing state-of-the-art salient object detection networks rely on aggregating multi-level features of pre-trained convolutional neural networks (CNNs). Compared to high-level features, low-level features contribute less to performance but…

Computer Vision and Pattern Recognition · Computer Science 2019-04-19 Zhe Wu , Li Su , Qingming Huang

In recent years, Fully Convolutional Networks (FCN) has been widely used in various semantic segmentation tasks, including multi-modal remote sensing imagery. How to fuse multi-modal data to improve the segmentation performance has always…

Computer Vision and Pattern Recognition · Computer Science 2018-07-25 Shihao Sun , Lei Yang , Wenjie Liu , Ruirui Li

Fully convolutional neural networks give accurate, per-pixel prediction for input images and have applications like semantic segmentation. However, a typical FCN usually requires lots of floating point computation and large run-time memory,…

Computer Vision and Pattern Recognition · Computer Science 2016-12-02 He Wen , Shuchang Zhou , Zhe Liang , Yuxiang Zhang , Dieqiao Feng , Xinyu Zhou , Cong Yao

Semantic segmentation is an essential part of deep learning. In recent years, with the development of remote sensing big data, semantic segmentation has been increasingly used in remote sensing. Deep convolutional neural networks (DCNNs)…

Computer Vision and Pattern Recognition · Computer Science 2021-05-31 Xuan Yang , Shanshan Li , Zhengchao Chen , Jocelyn Chanussot , Xiuping Jia , Bing Zhang , Baipeng Li , Pan Chen

High resolution is crucial for precise segmentation in fundus images, yet handling high-resolution inputs incurs considerable GPU memory costs, with diminishing performance gains as overhead increases. To address this issue while tackling…

Computer Vision and Pattern Recognition · Computer Science 2025-04-14 Ziyuan Ding , Yixiong Liang , Shichao Kan , Qing Liu

Semantic segmentation with deep learning has achieved great progress in classifying the pixels in the image. However, the local location information is usually ignored in the high-level feature extraction by the deep learning, which is…

Computer Vision and Pattern Recognition · Computer Science 2020-01-03 Yi Lu , Yaran Chen , Dongbin Zhao , Jianxin Chen

Holographic displays have significant potential in virtual reality and augmented reality owing to their ability to provide all the depth cues. Deep learning-based methods play an important role in computer-generated holography (CGH). During…

Optics · Physics 2025-11-11 Shuyang Xie , Jie Zhou , Bo Xu , Jun Wang , Renjing Xu

We present region-based, fully convolutional networks for accurate and efficient object detection. In contrast to previous region-based detectors such as Fast/Faster R-CNN that apply a costly per-region subnetwork hundreds of times, our…

Computer Vision and Pattern Recognition · Computer Science 2023-12-12 Jifeng Dai , Yi Li , Kaiming He , Jian Sun

We propose a method for high-performance semantic image segmentation (or semantic pixel labelling) based on very deep residual networks, which achieves the state-of-the-art performance. A few design factors are carefully considered to this…

Computer Vision and Pattern Recognition · Computer Science 2016-04-18 Zifeng Wu , Chunhua Shen , Anton van den Hengel

Fully convolutional networks (FCN) has significantly improved the performance of many pixel-labeling tasks, such as semantic segmentation and depth estimation. However, it still remains non-trivial to thoroughly utilize the multi-level…

Computer Vision and Pattern Recognition · Computer Science 2018-12-05 Yunzhi Zhuge , Pingping Zhang , Huchuan Lu

High-resolution representation learning plays an essential role in many vision problems, e.g., pose estimation and semantic segmentation. The high-resolution network (HRNet)~\cite{SunXLW19}, recently developed for human pose estimation,…

Computer Vision and Pattern Recognition · Computer Science 2019-04-10 Ke Sun , Yang Zhao , Borui Jiang , Tianheng Cheng , Bin Xiao , Dong Liu , Yadong Mu , Xinggang Wang , Wenyu Liu , Jingdong Wang