English
Related papers

Related papers: Redefining the Down-Sampling Scheme of U-Net for P…

200 papers

Recent researches have achieved great progress on single image super-resolution(SISR) due to the development of deep learning in the field of computer vision. In these method, the high resolution input image is down-scaled to low resolution…

Image and Video Processing · Electrical Eng. & Systems 2021-01-12 Zhengyang Lu , Ying Chen

The U-net architecture has significantly impacted deep learning-based segmentation of medical images. Through the integration of long-range skip connections, it facilitated the preservation of high-resolution features. Out-of-distribution…

Image and Video Processing · Electrical Eng. & Systems 2024-10-28 Frauke Wilm , Jonas Ammeling , Mathias Öttl , Rutger H. J. Fick , Marc Aubreville , Katharina Breininger

Existing studies tend tofocus onmodel modifications and integration with higher accuracy, which improve performance but also carry huge computational costs, resulting in longer detection times. Inmedical imaging, the use of time is…

Image and Video Processing · Electrical Eng. & Systems 2023-02-22 Weihu Song , Heng Yu

In convolutional neural networks (CNNs), downsampling operations are crucial to model performance. Although traditional downsampling methods (such as maximum pooling and cross-row convolution) perform well in feature aggregation, receptive…

Computer Vision and Pattern Recognition · Computer Science 2025-07-22 Wenbo Yue , Chang Li , Guoping Xu

Data scarcity is a major challenge in medical imaging, particularly for deep learning models. While data pooling (combining datasets from multiple sources) and data addition (adding more data from a new dataset) have been shown to enhance…

Computer Vision and Pattern Recognition · Computer Science 2026-02-27 Ayush Roy , Samin Enam , Jun Xia , Won Hwa Kim , Vishnu Suresh Lokhande

Many computer vision systems require low-cost segmentation algorithms based on deep learning, either because of the enormous size of input images or limited computational budget. Common solutions uniformly downsample the input images to…

Computer Vision and Pattern Recognition · Computer Science 2022-08-19 Chen Jin , Ryutaro Tanno , Thomy Mertzanidou , Eleftheria Panagiotaki , Daniel C. Alexander

Semantic segmentation for medical 3D image stacks enables accurate volumetric reconstructions, computer-aided diagnostics and follow up treatment planning. In this work, we present a novel variant of the Unet model called the NUMSnet that…

Image and Video Processing · Electrical Eng. & Systems 2023-04-07 Sohini Roychowdhury

Downsampling images and labels, often necessitated by limited resources or to expedite network training, leads to the loss of small objects and thin boundaries. This undermines the segmentation network's capacity to interpret images…

Image and Video Processing · Electrical Eng. & Systems 2024-10-27 Shahzad Ali , Yu Rim Lee , Soo Young Park , Won Young Tak , Soon Ki Jung

There is large consent that successful training of deep networks requires many thousand annotated training samples. In this paper, we present a network and training strategy that relies on the strong use of data augmentation to use the…

Computer Vision and Pattern Recognition · Computer Science 2015-05-19 Olaf Ronneberger , Philipp Fischer , Thomas Brox

U-shaped networks and its variants have demonstrated exceptional results for medical image segmentation. In this paper, we propose a novel dual self-distillation (DSD) framework in U-shaped networks for volumetric medical image…

Image and Video Processing · Electrical Eng. & Systems 2025-05-05 Soumyanil Banerjee , Nicholas Summerfield , Ming Dong , Carri Glide-Hurst

Feature pooling layers (e.g., max pooling) in convolutional neural networks (CNNs) serve the dual purpose of providing increasingly abstract representations as well as yielding computational savings in subsequent convolutional layers. We…

Machine Learning · Computer Science 2016-11-17 Shuangfei Zhai , Hui Wu , Abhishek Kumar , Yu Cheng , Yongxi Lu , Zhongfei Zhang , Rogerio Feris

In this paper, we introduce U-Net v2, a new robust and efficient U-Net variant for medical image segmentation. It aims to augment the infusion of semantic information into low-level features while simultaneously refining high-level features…

Image and Video Processing · Electrical Eng. & Systems 2024-04-02 Yaopeng Peng , Milan Sonka , Danny Z. Chen

Accurate segmentation of the pelvic CTs is crucial for the clinical diagnosis of pelvic bone diseases and for planning patient-specific hip surgeries. With the emergence and advancements of deep learning for digital healthcare, several…

Image and Video Processing · Electrical Eng. & Systems 2021-01-28 Prabhakara Subramanya Jois , Aniketh Manjunath , Thomas Fevens

Semantic image segmentation is the process of labeling each pixel of an image with its corresponding class. An encoder-decoder based approach, like U-Net and its variants, is a popular strategy for solving medical image segmentation tasks.…

Image and Video Processing · Electrical Eng. & Systems 2020-06-30 Debesh Jha , Michael A. Riegler , Dag Johansen , Pål Halvorsen , Håvard D. Johansen

Downsampling is widely adopted to achieve a good trade-off between accuracy and latency for visual recognition. Unfortunately, the commonly used pooling layers are not learned, and thus cannot preserve important information. As another…

Computer Vision and Pattern Recognition · Computer Science 2022-07-26 Ho Man Kwan , Shenghui Song

U-Net has been providing state-of-the-art performance in many medical image segmentation problems. Many modifications have been proposed for U-Net, such as attention U-Net, recurrent residual convolutional U-Net (R2-UNet), and U-Net with…

Computer Vision and Pattern Recognition · Computer Science 2019-08-29 Juntang Zhuang

Image segmentation is a fundamental task in image analysis and clinical practice. The current state-of-the-art techniques are based on U-shape type encoder-decoder networks with skip connections, called U-Net. Despite the powerful…

Computer Vision and Pattern Recognition · Computer Science 2023-02-02 Chun-Wun Cheng , Christina Runkel , Lihao Liu , Raymond H Chan , Carola-Bibiane Schönlieb , Angelica I Aviles-Rivero

The traditional SegNet architecture commonly encounters significant information loss during the sampling process, which detrimentally affects its accuracy in image semantic segmentation tasks. To counter this challenge, we introduce an…

Image and Video Processing · Electrical Eng. & Systems 2024-06-05 Zijun Gao , Qi Wang , Taiyuan Mei , Xiaohan Cheng , Yun Zi , Haowei Yang

Convolutional Neural Networks (CNNs) use pooling to decrease the size of activation maps. This process is crucial to increase the receptive fields and to reduce computational requirements of subsequent convolutions. An important feature of…

Computer Vision and Pattern Recognition · Computer Science 2021-03-19 Alexandros Stergiou , Ronald Poppe , Grigorios Kalliatakis

Many imaging tasks require global information about all pixels in an image. Conventional bottom-up classification networks globalize information by decreasing resolution; features are pooled and downsampled into a single output. But for…

Computer Vision and Pattern Recognition · Computer Science 2018-04-30 Sohil Shah , Pallabi Ghosh , Larry S Davis , Tom Goldstein
‹ Prev 1 2 3 10 Next ›