中文
相关论文

相关论文: Improving the Robustness of Capsule Networks to Im…

200 篇论文

Capsule Network (CapsNet) is among the promising classifiers and a possible successor of the classifiers built based on Convolutional Neural Network (CNN). CapsNet is more accurate than CNNs in detecting images with overlapping categories…

计算机视觉与模式识别 · 计算机科学 2025-12-02 Pouya Shiri , Amirali Baniasadi

In this work, we address the problem of improvement of robustness of feature representations learned using convolutional neural networks (CNNs) to image deformation. We argue that higher moment statistics of feature distributions could be…

计算机视觉与模式识别 · 计算机科学 2017-07-26 Zhun Sun , Mete Ozay , Takayuki Okatani

Convolutional neural networks (CNNs) have become a key asset to most of fields in AI. Despite their successful performance, CNNs suffer from a major drawback. They fail to capture the hierarchy of spatial relation among different parts of…

计算机视觉与模式识别 · 计算机科学 2020-02-10 Marzieh Edraki , Nazanin Rahnavard , Mubarak Shah

Convolutional Neural Networks have dramatically improved in recent years, surpassing human accuracy on certain problems and performance exceeding that of traditional computer vision algorithms. While the compute pattern in itself is…

计算机视觉与模式识别 · 计算机科学 2018-07-10 Michaela Blott , Thomas B. Preusser , Nicholas Fraser , Giulio Gambardella , Kenneth OBrien , Yaman Umuroglu , Miriam Leeser

Convolutional neural networks (CNNs) have shown great capability of solving various artificial intelligence tasks. However, the increasing model size has raised challenges in employing them in resource-limited applications. In this work, we…

计算机视觉与模式识别 · 计算机科学 2018-09-06 Hongyang Gao , Zhengyang Wang , Shuiwang Ji

Capsule Networks (CapsNets) have demonstrated to be a promising alternative to Convolutional Neural Networks (CNNs). However, they often fall short of state-of-the-art accuracies on large-scale high-dimensional datasets. We propose a…

计算机视觉与模式识别 · 计算机科学 2020-07-13 Aryan Mobiny , Pengyu Yuan , Pietro Antonio Cicalese , Hien Van Nguyen

Capsule Networks (CapsNets) have been proposed as an alternative to Convolutional Neural Networks (CNNs). This paper showcases how CapsNets are more capable than CNNs for autonomous agent exploration of realistic scenarios. In real world…

机器学习 · 计算机科学 2020-02-11 Thomas Molnar , Eugenio Culurciello

Despite enjoying desirable efficiency and reduced reliance on domain expertise, existing neural methods for vehicle routing problems (VRPs) suffer from severe robustness issues -- their performance significantly deteriorates on clean…

人工智能 · 计算机科学 2024-10-08 Jianan Zhou , Yaoxin Wu , Zhiguang Cao , Wen Song , Jie Zhang , Zhiqi Shen

Deep Neural Networks (DNNs) have been widely deployed for many Machine Learning applications. Recently, CapsuleNets have overtaken traditional DNNs, because of their improved generalization ability due to the multi-dimensional capsules, in…

分布式、并行与集群计算 · 计算机科学 2021-01-26 Alberto Marchisio , Muhammad Abdullah Hanif , Muhammad Shafique

Image classification is a challenging problem which aims to identify the category of object in the image. In recent years, deep Convolutional Neural Networks (CNNs) have been applied to handle this task, and impressive improvement has been…

计算机视觉与模式识别 · 计算机科学 2022-11-29 Hao Ren , Jianlin Su , Hong Lu

As clean ImageNet accuracy nears its ceiling, the research community is increasingly more concerned about robust accuracy under distributional shifts. While a variety of methods have been proposed to robustify neural networks, these…

计算机视觉与模式识别 · 计算机科学 2022-04-11 Yutaro Yamada , Mayu Otani

Capsule Networks outperform Convolutional Neural Networks in learning the part-whole relationships with viewpoint invariance, and the credit goes to their multidimensional capsules. It was assumed that increasing the number of capsule…

计算机视觉与模式识别 · 计算机科学 2024-10-23 Siddharth Sahu , Abdulrahman Altahhan

Lung cancer is the leading cause of cancer-related deaths in the past several years. A major challenge in lung cancer screening is the detection of lung nodules from computed tomography (CT) scans. State-of-the-art approaches in automated…

计算机视觉与模式识别 · 计算机科学 2018-10-05 Aryan Mobiny , Hien Van Nguyen

Recently, very deep convolutional neural networks (CNNs) have shown outstanding performance in object recognition and have also been the first choice for dense classification problems such as semantic segmentation. However, repeated…

计算机视觉与模式识别 · 计算机科学 2016-11-28 Guosheng Lin , Anton Milan , Chunhua Shen , Ian Reid

Convolutional neural networks (CNNs) are inherently limited to model geometric transformations due to the fixed geometric structures in its building modules. In this work, we introduce two new modules to enhance the transformation modeling…

计算机视觉与模式识别 · 计算机科学 2017-06-06 Jifeng Dai , Haozhi Qi , Yuwen Xiong , Yi Li , Guodong Zhang , Han Hu , Yichen Wei

Convolutional Neural Networks (ConvNets) are commonly developed at a fixed resource budget, and then scaled up for better accuracy if more resources are available. In this paper, we systematically study model scaling and identify that…

机器学习 · 计算机科学 2020-09-14 Mingxing Tan , Quoc V. Le

Convolutional Neural Networks (CNNs) have achieved promising results in medical image segmentation. However, CNNs require lots of training data and are incapable of handling pose and deformation of objects. Furthermore, their pooling layers…

计算机视觉与模式识别 · 计算机科学 2022-06-28 Minh Tran , Viet-Khoa Vo-Ho , Ngan T. H. Le

Convolutional neural networks (CNNs) have demonstrated remarkable results in image classification for benchmark tasks and practical applications. The CNNs with deeper architectures have achieved even higher performance recently thanks to…

计算机视觉与模式识别 · 计算机科学 2019-04-15 Ryo Takahashi , Takashi Matsubara , Kuniaki Uehara

Capsule networks are a recently developed class of neural networks that potentially address some of the deficiencies with traditional convolutional neural networks. By replacing the standard scalar activations with vectors, and by…

机器学习 · 计算机科学 2020-01-30 Arjun Punjabi , Jonas Schmid , Aggelos K. Katsaggelos

This paper proposes a user semantic intent modeling algorithm based on Capsule Networks to address the problem of insufficient accuracy in intent recognition for human-computer interaction. The method represents semantic features in input…

计算与语言 · 计算机科学 2025-07-02 Shixiao Wang , Yifan Zhuang , Runsheng Zhang , Zhijun Song