English
Related papers

Related papers: Dynamic Region-Aware Convolution

200 papers

3D spatial information is known to be beneficial to the semantic segmentation task. Most existing methods take 3D spatial data as an additional input, leading to a two-stream segmentation network that processes RGB and 3D spatial…

Computer Vision and Pattern Recognition · Computer Science 2021-02-24 Lin-Zhuo Chen , Zheng Lin , Ziqin Wang , Yong-Liang Yang , Ming-Ming Cheng

Most image denoising networks apply a single set of static convolutional kernels across the entire input image. This is sub-optimal for natural images, as they often consist of heterogeneous visual patterns. Dynamic convolution tries to…

Computer Vision and Pattern Recognition · Computer Science 2022-08-10 Yifan Jiang , Bartlomiej Wronski , Ben Mildenhall , Jonathan T. Barron , Zhangyang Wang , Tianfan Xue

Group convolution, which divides the channels of ConvNets into groups, has achieved impressive improvement over the regular convolution operation. However, existing models, eg. ResNeXt, still suffers from the sub-optimal performance due to…

Computer Vision and Pattern Recognition · Computer Science 2019-08-20 Zhaoyang Zhang , Jingyu Li , Wenqi Shao , Zhanglin Peng , Ruimao Zhang , Xiaogang Wang , Ping Luo

Convolution as inner product has been the founding basis of convolutional neural networks (CNNs) and the key to end-to-end visual representation learning. Benefiting from deeper architectures, recent CNNs have demonstrated increasingly…

Machine Learning · Computer Science 2018-01-31 Weiyang Liu , Yan-Ming Zhang , Xingguo Li , Zhiding Yu , Bo Dai , Tuo Zhao , Le Song

Deep neural networks are playing an important role in state-of-the-art visual recognition. To represent high-level visual concepts, modern networks are equipped with large convolutional layers, which use a large number of filters and…

Computer Vision and Pattern Recognition · Computer Science 2017-03-06 Yan Wang , Lingxi Xie , Ya Zhang , Wenjun Zhang , Alan Yuille

Convolutional Neural Network (CNN) has demonstrated impressive ability to represent hyperspectral images and to achieve promising results in hyperspectral image classification. However, traditional CNN models can only operate convolution on…

Image and Video Processing · Electrical Eng. & Systems 2019-05-16 Sheng Wan , Chen Gong , Ping Zhong , Bo Du , Lefei Zhang , Jian Yang

In Neural Networks, there are various methods of feature fusion. Different strategies can significantly affect the effectiveness of feature representation, consequently influencing the ability of model to extract representative and…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Si Zhou , Yain-Whar Si , Xiaochen Yuan , Xiaofan Li , Xiaoxiang Liu , Xinyuan Zhang , Cong Lin , Xueyuan Gong

We propose contextual convolution (CoConv) for visual recognition. CoConv is a direct replacement of the standard convolution, which is the core component of convolutional neural networks. CoConv is implicitly equipped with the capability…

Computer Vision and Pattern Recognition · Computer Science 2021-08-18 Ionut Cosmin Duta , Mariana Iuliana Georgescu , Radu Tudor Ionescu

The spatial attention mechanism has been widely used to improve object detection performance. However, its operation is currently limited to static convolutions lacking content-adaptive features. This paper innovatively approaches from the…

Computer Vision and Pattern Recognition · Computer Science 2024-03-28 Wenjie Xing , Zhenchao Cui , Jing Qi

Deep convolutional networks have attracted great attention in image restoration and enhancement. Generally, restoration quality has been improved by building more and more convolutional block. However, these methods mostly learn a specific…

Computer Vision and Pattern Recognition · Computer Science 2021-05-21 Yukai Shi , Jinghui Qin

We propose Re-parameterized Refocusing Convolution (RefConv) as a replacement for regular convolutional layers, which is a plug-and-play module to improve the performance without any inference costs. Specifically, given a pre-trained model,…

Computer Vision and Pattern Recognition · Computer Science 2023-10-17 Zhicheng Cai , Xiaohan Ding , Qiu Shen , Xun Cao

We present a new convolutional neural network, called Multi Voxel-Point Neurons Convolution (MVPConv), for fast and accurate 3D deep learning. The previous works adopt either individual point-based features or local-neighboring voxel-based…

Computer Vision and Pattern Recognition · Computer Science 2021-05-03 Wei Zhou , Xin Cao , Xiaodan Zhang , Xingxing Hao , Dekui Wang , Ying He

High-dimensional generative models have many applications including image compression, multimedia generation, anomaly detection and data completion. State-of-the-art estimators for natural images are autoregressive, decomposing the joint…

Machine Learning · Computer Science 2020-06-30 Ajay Jain , Pieter Abbeel , Deepak Pathak

Recently, convolutional neural networks (CNNs) have been widely used in sound event detection (SED). However, traditional convolution is deficient in learning time-frequency domain representation of different sound events. To address this…

Audio and Speech Processing · Electrical Eng. & Systems 2023-02-22 Shengchang Xiao , Xueshuai Zhang , Pengyuan Zhang

Convolutional Neural Networks (CNNs) have recently been shown to excel at performing visual place recognition under changing appearance and viewpoint. Previously, place recognition has been improved by intelligently selecting relevant…

Robotics · Computer Science 2018-10-31 Stephen Hausler , Adam Jacobson , Michael Milford

Learned image compression (LIC) has recently made significant progress, surpassing traditional methods. However, most LIC approaches operate mainly in the spatial domain and lack mechanisms for reducing frequency-domain correlations. To…

Computer Vision and Pattern Recognition · Computer Science 2025-04-08 Haisheng Fu , Jie Liang , Feng Liang , Zhenman Fang , Guohe Zhang , Jingning Han

Convolutional Neural Networks (CNNs) have exhibited their great power in a variety of vision tasks. However, the lack of transform-invariant property limits their further applications in complicated real-world scenarios. In this work, we…

Computer Vision and Pattern Recognition · Computer Science 2022-01-19 Tong Zhang , Haohan Weng , Ke Yi , C. L. Philip Chen

Unlike images which are represented in regular dense grids, 3D point clouds are irregular and unordered, hence applying convolution on them can be difficult. In this paper, we extend the dynamic filter to a new convolution operation, named…

Computer Vision and Pattern Recognition · Computer Science 2020-11-11 Wenxuan Wu , Zhongang Qi , Li Fuxin

Transformers have captured growing attention in computer vision, thanks to its large capacity and global processing capabilities. However, transformers are data hungry, and their ability to generalize is constrained compared to…

Computer Vision and Pattern Recognition · Computer Science 2025-08-26 Hosam S. EL-Assiouti , Hadeer El-Saadawy , Maryam N. Al-Berry , Mohamed F. Tolba

The performance of local feature descriptors degrades in the presence of large rotation variations. To address this issue, we present an efficient approach to learning rotation invariant descriptors. Specifically, we propose Rotated Kernel…

Computer Vision and Pattern Recognition · Computer Science 2024-01-08 Ranran Huang , Jiancheng Cai , Chao Li , Zhuoyuan Wu , Xinmin Liu , Zhenhua Chai