Results 261 to 270 of about 1,031,506 (314)

LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation

Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, 2020
Graph Convolution Network (GCN) has become new state-of-the-art for collaborative filtering. Nevertheless, the reasons of its effectiveness for recommendation are not well understood.
Xiangnan He, Kuan Deng, Xiang Wang, Yan Li, Yongdong Zhang, Meng Wang   +5 more
semanticscholar   +1 more source

SCConv: Spatial and Channel Reconstruction Convolution for Feature Redundancy

Computer Vision and Pattern Recognition, 2023
Convolutional Neural Networks (CNNs) have achieved remarkable performance in various computer vision tasks but this comes at the cost of tremendous computational resources, partly due to convolutional layers extracting redundant features.
Jiafeng Li, Ying Wen, Lianghua He
semanticscholar   +1 more source

RFAConv: Receptive-field attention convolution for improving convolutional neural networks

Pattern Recognition, 2023
In the realm of deep learning, spatial attention mechanisms have emerged as a vital method for enhancing the performance of convolutional neural networks. However, these mechanisms possess inherent limitations that cannot be overlooked.
X. Zhang, Chen Liu, Degang Yang, Tingting Song, Yichen Ye, Ke Li, Ying Song   +6 more
semanticscholar   +1 more source

Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation

European Conference on Computer Vision, 2018
Spatial pyramid pooling module or encode-decoder structure are used in deep neural networks for semantic segmentation task. The former networks are able to encode multi-scale contextual information by probing the incoming features with filters or pooling
Liang-Chieh Chen, Yukun Zhu, G. Papandreou, Florian Schroff, Hartwig Adam   +4 more
semanticscholar   +1 more source

SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction

Neural Information Processing Systems, 2021
One unique property of time series is that the temporal relations are largely preserved after downsampling into two sub-sequences. By taking advantage of this property, we propose a novel neural network architecture that conducts sample convolution and ...
Minhao Liu, Ailing Zeng, Mu-Hwa Chen, Zhijian Xu, Qiuxia Lai, Lingna Ma, Qiang Xu   +6 more
semanticscholar   +1 more source

Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution

European Conference on Computer Vision, 2020
Self-driving cars need to understand 3D scenes efficiently and accurately in order to drive safely. Given the limited hardware resources, existing 3D perception models are not able to recognize small instances (e.g., pedestrians, cyclists) very well due ...
Haotian Tang, Zhijian Liu, Shengyu Zhao, Yujun Lin, Ji Lin, Hanrui Wang, Song Han   +6 more
semanticscholar   +1 more source

LDConv: Linear deformable convolution for improving convolutional neural networks

Image and Vision Computing, 2023
Neural networks based on convolutional operations have achieved remarkable results in the field of deep learning, but there are two inherent flaws in standard convolutional operations.
Xin Zhang, Yingze Song, Tingting Song, Degang Yang, Yichen Ye, Jie Zhou, Liming Zhang   +6 more
semanticscholar   +1 more source

Convolution Rings

Algebra Colloquium, 2006
The notion of a convolution type is introduced. Imposing such a type on a ring gives the corresponding convolution ring. Under this umbrella, a wide variety of ring constructions can be covered, including polynomials, matrices, incidence algebras, necklace rings, group rings and quaternion rings.
openaire   +1 more source

FERMI CONVOLUTION

Infinite Dimensional Analysis, Quantum Probability and Related Topics, 2002
Below a new kind of convolution is introduced for probability measures, whose combinatorics is related to non-crossing partitions without inner blocks other than singletons — the partitions corresponding to the fermionic creation and annihilation operators and Pauli's principle.
openaire   +2 more sources