English
Related papers

Related papers: Malleable 2.5D Convolution: Learning Receptive Fie…

200 papers

State-of-the-art 2D image compression schemes rely on the power of convolutional neural networks (CNNs). Although CNNs offer promising perspectives for 2D image compression, extending such models to omnidirectional images is not…

Image and Video Processing · Electrical Eng. & Systems 2022-09-21 Navid Mahmoudian Bidgoli , Roberto G. de A. Azevedo , Thomas Maugey , Aline Roumy , Pascal Frossard

Recent advances in scene understanding benefit a lot from depth maps because of the 3D geometry information, especially in complex conditions (e.g., low light and overexposed). Existing approaches encode depth maps along with RGB images and…

Computer Vision and Pattern Recognition · Computer Science 2025-04-08 Bo-Wen Yin , Jiao-Long Cao , Ming-Ming Cheng , Qibin Hou

Many convolutional neural networks (CNNs) rely on progressive downsampling of their feature maps to increase the network's receptive field and decrease computational cost. However, this comes at the price of losing granularity in the…

Computer Vision and Pattern Recognition · Computer Science 2023-05-17 Robin Hesse , Simone Schaub-Meyer , Stefan Roth

Attention mechanism plays a more and more important role in point cloud analysis and channel attention is one of the hotspots. With so much channel information, it is difficult for neural networks to screen useful channel information. Thus,…

Computer Vision and Pattern Recognition · Computer Science 2021-12-07 Guoquan Xu , Hezhi Cao , Yifan Zhang , Jianwei Wan , Ke Xu , Yanxin Ma

This paper proposes a new deep convolutional neural network (DCNN) architecture that learns pixel embeddings, such that pairwise distances between the embeddings can be used to infer whether or not the pixels lie on the same region. That…

Computer Vision and Pattern Recognition · Computer Science 2016-01-11 Adam W. Harley , Konstantinos G. Derpanis , Iasonas Kokkinos

Nonlocal self-similarity within images has become an increasingly popular prior in deep-learning models. Despite their successful image restoration performance, such models remain largely uninterpretable due to their black-box construction.…

Image and Video Processing · Electrical Eng. & Systems 2026-02-06 Nikola Janjusevic , Amirhossein Khalilian-Gourtani , Adeen Flinker , Li Feng , Yao Wang

Many deep neural networks are built by using stacked convolutional layers of fixed and single size (often 3$\times$3) kernels. This paper describes a method for training the size of convolutional kernels to provide varying size kernels in a…

Computer Vision and Pattern Recognition · Computer Science 2020-09-15 F. Boray Tek , İlker Çam , Deniz Karlı

Standard convolutional neural networks assume a grid structured input is available and exploit discrete convolutions as their fundamental building blocks. This limits their applicability to many real-world applications. In this paper we…

Computer Vision and Pattern Recognition · Computer Science 2021-01-19 Shenlong Wang , Simon Suo , Wei-Chiu Ma , Andrei Pokrovsky , Raquel Urtasun

We propose a novel iterative method to adapt a a graph to d-dimensional image data. The method drives the nodes of the graph towards image features. The adaptation process naturally lends itself to a measure of feature saliency which can…

Computer Vision and Pattern Recognition · Computer Science 2019-09-06 Alberto Gomez , Veronika A. Zimmer , Bishesh Khanal , Nicolas Toussaint , Julia A. Schnabel

3D point clouds deep learning is a promising field of research that allows a neural network to learn features of point clouds directly, making it a robust tool for solving 3D scene understanding tasks. While recent works show that point…

Computer Vision and Pattern Recognition · Computer Science 2022-03-22 Zhiyuan Zhang , Binh-Son Hua , Sai-Kit Yeung

In this study, we address the challenge of 3D scene structure recovery from monocular depth estimation. While traditional depth estimation methods leverage labeled datasets to directly predict absolute depth, recent advancements advocate…

Computer Vision and Pattern Recognition · Computer Science 2023-09-19 Chi Zhang , Wei Yin , Gang Yu , Zhibin Wang , Tao Chen , Bin Fu , Joey Tianyi Zhou , Chunhua Shen

Infrared small target detection (ISTD) is critical in both civilian and military applications. However, the limited texture and structural information in infrared images makes accurate detection particularly challenging. Although recent…

Computer Vision and Pattern Recognition · Computer Science 2025-05-26 Xingye Cui , Junhai Luo , Jiakun Deng , Kexuan Li , Xiangyu Qiu , Zhenming Peng

Contextual information is crucial for semantic segmentation. However, finding the optimal trade-off between keeping desired fine details and at the same time providing sufficiently large receptive fields is non trivial. This is even more…

Computer Vision and Pattern Recognition · Computer Science 2017-09-08 Yang He , Margret Keuper , Bernt Schiele , Mario Fritz

An important goal in visual recognition is to devise image representations that are invariant to particular transformations. In this paper, we address this goal with a new type of convolutional neural network (CNN) whose invariance is…

Computer Vision and Pattern Recognition · Computer Science 2015-01-08 Julien Mairal , Piotr Koniusz , Zaid Harchaoui , Cordelia Schmid

Deep learning is currently playing a crucial role toward higher levels of artificial intelligence. This paradigm allows neural networks to learn complex and abstract representations, that are progressively obtained by combining simpler…

Audio and Speech Processing · Electrical Eng. & Systems 2019-08-12 Mirco Ravanelli , Yoshua Bengio

Standard 3D convolution operations require much larger amounts of memory and computation cost than 2D convolution operations. The fact has hindered the development of deep neural nets in many 3D vision tasks. In this paper, we investigate…

Computer Vision and Pattern Recognition · Computer Science 2018-08-07 Rongtian Ye , Fangyu Liu , Liqiang Zhang

We propose a principled convolutional neural pyramid (CNP) framework for general low-level vision and image processing tasks. It is based on the essential finding that many applications require large receptive fields for structure…

Computer Vision and Pattern Recognition · Computer Science 2017-04-10 Xiaoyong Shen , Ying-Cong Chen , Xin Tao , Jiaya Jia

Despite the tremendous achievements of deep convolutional neural networks (CNNs) in many computer vision tasks, understanding how they actually work remains a significant challenge. In this paper, we propose a novel two-step understanding…

Computer Vision and Pattern Recognition · Computer Science 2019-04-02 Heyi Li , Yunke Tian , Klaus Mueller , Xin Chen

Learning on evolving(dynamic) graphs has caught the attention of researchers as static methods exhibit limited performance in this setting. The existing methods for dynamic graphs learn spatial features by local neighborhood aggregation,…

Machine Learning · Computer Science 2022-11-23 Anson Bastos , Abhishek Nadgeri , Kuldeep Singh , Toyotaro Suzumura , Manish Singh

Convolutional neural networks (CNNs) have achieved great success on grid-like data such as images, but face tremendous challenges in learning from more generic data such as graphs. In CNNs, the trainable local filters enable the automatic…

Machine Learning · Computer Science 2018-09-05 Hongyang Gao , Zhengyang Wang , Shuiwang Ji