English
Related papers

Related papers: X-volution: On the unification of convolution and …

200 papers

Deep learning has made important contributions to the development of medical image segmentation. Convolutional neural networks, as a crucial branch, have attracted strong attention from researchers. Through the tireless efforts of numerous…

Image and Video Processing · Electrical Eng. & Systems 2024-05-02 Zhaojin Fu , Zheng Chen , Jinjiang Li , Lu Ren

Deep image hashing aims to map input images into simple binary hash codes via deep neural networks and thus enable effective large-scale image retrieval. Recently, hybrid networks that combine convolution and Transformer have achieved…

Computer Vision and Pattern Recognition · Computer Science 2024-05-15 Chao He , Hongxi Wei

In recent years, deep learning has achieved great success in many computer vision applications. Convolutional neural networks (CNNs) have lately emerged as a major approach to image classification. Most research on CNNs thus far has focused…

Computer Vision and Pattern Recognition · Computer Science 2017-03-28 Yunho Jeon , Junmo Kim

Recently, Deep Convolution Networks (DCNNs) have been applied to the task of face alignment and have shown potential for learning improved feature representations. Although deeper layers can capture abstract concepts like pose, it is…

Computer Vision and Pattern Recognition · Computer Science 2017-04-07 Amit Kumar , Rama Chellappa

Graph convolutional networks (GCNs) have achieved remarkable learning ability for dealing with various graph structural data recently. In general, deep GCNs do not work well since graph convolution in conventional GCNs is a special form of…

Machine Learning · Computer Science 2021-12-08 Zhilong Xiong , Jia Cai

Like other applications in computer vision, medical image segmentation has been most successfully addressed using deep learning models that rely on the convolution operation as their main building block. Convolutions enjoy important…

Image and Video Processing · Electrical Eng. & Systems 2022-04-05 Davood Karimi , Serge Vasylechko , Ali Gholipour

Deep learning on the point cloud is increasingly developing. Grouping the point with its neighbors and conducting convolution-like operation on them can learn the local feature of the point cloud, but this method is weak to extract the…

Computer Vision and Pattern Recognition · Computer Science 2021-12-01 Shangwei Guo , Jun Li , Zhengchao Lai , Xiantong Meng , Shaokun Han

Convolutional neural networks (CNNs) evaluate short-range correlations in input images which progress along the layers, whereas vision transformer (ViT) architectures evaluate long-range correlations, using repeated transformer encoders…

Machine Learning · Computer Science 2025-04-10 Ella Koresh , Ronit D. Gross , Yuval Meir , Yarden Tzach , Tal Halevi , Ido Kanter

Deep neural networks employ specialized architectures for vision, sequential and language tasks, yet this proliferation obscures their underlying commonalities. We introduce a unified matrix-order framework that casts convolutional,…

Machine Learning · Computer Science 2025-07-24 Yuzhou Zhu

In this paper we propose cross-modal convolutional neural networks (X-CNNs), a novel biologically inspired type of CNN architectures, treating gradient descent-specialised CNNs as individual units of processing in a larger-scale network…

Machine Learning · Statistics 2017-09-26 Petar Veličković , Duo Wang , Nicholas D. Lane , Pietro Liò

The current trend of automating inspections at substations has sparked a surge in interest in the field of transformer image recognition. However, due to restrictions in the number of parameters in existing models, high-resolution images…

Computer Vision and Pattern Recognition · Computer Science 2023-12-08 Siyi Zhang , Cheng Liu , Xiang Li , Xin Zhai , Zhen Wei , Sizhe Li , Xun Ma

Recent advances in vision transformers (ViTs) have achieved great performance in visual recognition tasks. Convolutional neural networks (CNNs) exploit spatial inductive bias to learn visual representations, but these networks are spatially…

Computer Vision and Pattern Recognition · Computer Science 2023-07-06 Youpeng Zhao , Huadong Tang , Yingying Jiang , Yong A , Qiang Wu

Although transformers have become the neural architectures of choice for natural language processing, they require orders of magnitude more training data, GPU memory, and computations in order to compete with convolutional neural networks…

Computer Vision and Pattern Recognition · Computer Science 2021-10-04 Pranav Jeevan , Amit Sethi

We introduce a new architecture for unsupervised object-centric representation learning and multi-object detection and segmentation, which uses a translation-equivariant attention mechanism to predict the coordinates of the objects present…

Computer Vision and Pattern Recognition · Computer Science 2022-09-01 Bruno Sauvalle , Arnaud de La Fortelle

Self-attention, as the key block of transformers, is a powerful mechanism for extracting features from the inputs. In essence, what self-attention does is to infer the pairwise relations between the elements of the inputs, and modify the…

Machine Learning · Computer Science 2021-03-09 Lemeng Wu , Xingchao Liu , Qiang Liu

Proto-objects - image regions that share common visual properties - offer a promising alternative to traditional attention mechanisms based on rectangular-shaped image patches in neural networks. Although previous work demonstrated that…

Neural and Evolutionary Computing · Computer Science 2025-05-02 Rafael C. Pinto , Anderson R. Tavares

Deep convolutional networks are ubiquitous in computer vision, due to their excellent performance across different tasks for various domains. Models are, however, often trained in isolation for each task, failing to exploit relatedness…

Computer Vision and Pattern Recognition · Computer Science 2023-07-18 Ekaterina Iakovleva , Karteek Alahari , Jakob Verbeek

Decoding human activity accurately from wearable sensors can aid in applications related to healthcare and context awareness. The present approaches in this domain use recurrent and/or convolutional models to capture the spatio-temporal…

Human-Computer Interaction · Computer Science 2020-12-21 Satya P. Singh , Aimé Lay-Ekuakille , Deepak Gangwar , Madan Kumar Sharma , Sukrit Gupta

This paper does not attempt to design a state-of-the-art method for visual recognition but investigates a more efficient way to make use of convolutions to encode spatial features. By comparing the design principles of the recent…

Computer Vision and Pattern Recognition · Computer Science 2022-11-23 Qibin Hou , Cheng-Ze Lu , Ming-Ming Cheng , Jiashi Feng

Encoder transformer models compress information from all tokens in a sequence into a single [CLS] token to represent global context. This approach risks diluting fine-grained or hierarchical features, leading to information loss in…

Computation and Language · Computer Science 2025-09-23 Asif Shahriar , Rifat Shahriyar , M Saifur Rahman