Results 121 to 130 of about 4,852 (165)

Frequency-aware vision transformers for high-fidelity super-resolution of Earth system models. [PDF]

Sci Rep
Zeraatkar E, Faroughi SA, Tešić J.
europepmc   +1 more source

Exact feature collisions in neural networks. [PDF]

Sci Rep
Ozbulak U, Rao S, De Neve W, Vankerschaver J, Van Messem A, Gasparyan M.   +5 more
europepmc   +1 more source

A Supervised Contrastive Variational Autoencoder with Probabilistic Latent Alignment for Cross-Domain EEG Emotion Recognition. [PDF]

Sensors (Basel)
Wu L, Yang Y, Wang W, Xie Y, Zhou N, Shi K.   +5 more
europepmc   +1 more source

Deep Convolutional Framelets for Dose Reconstruction in Boron Neutron Capture Therapy with Compton Camera Detector. [PDF]

Cancers (Basel)
Didonna A, Ramos Lopez D, Iaselli G, Amoroso N, Ferrara N, Pugliese GMI.   +5 more
europepmc   +1 more source

HAAU-Net: Hybrid Adaptive Attention U-Net Integrated with Context-Aware Morphologically Stable Features for Real-Time MRI Brain Tumor Detection and Segmentation. [PDF]

Tomography
Asghar MA, Shoaib S, Zahid M.
europepmc   +1 more source

A U-Net Improved Version for Crop and Weed Segmentation from Aerial Images. [PDF]

Sensors (Basel)
Bunica-Mihai A, Popescu D, Ichim L.
europepmc   +1 more source

Artificial intelligence in aortic CT angiography: current applications and future perspectives. [PDF]

Front Cardiovasc Med
Xu J, Liu J, Cao G.
europepmc   +1 more source

A neural network for modeling human concept formation, understanding and communication. [PDF]

Nat Comput Sci
Guo L, Chen H, Chen Y, Bi Y, Yu S.
europepmc   +1 more source

Early Tuberculosis Detection via Privacy-Preserving, Adaptive-Weighted Deep Models. [PDF]

Diagnostics (Basel)
Gasmi K, Alanazi A, Ben Aoun N, Altaieb MO, Abdalrahman AEM, Hamid O, Almenwer S, Ben Ammar L, Yahyaoui S, Mrabet M.   +9 more
europepmc   +1 more source

Some of the next articles are maybe not open access.

Related searches:

SRGC-Nets: Sparse Repeated Group Convolutional Neural Networks

IEEE Transactions on Neural Networks and Learning Systems, 2020
Group convolution is widely used in many mobile networks to remove the filter's redundancy from the channel extent. In order to further reduce the redundancy of group convolution, this article proposes a novel repeated group convolutional (RGC) kernel, which has M primary groups, and each primary group includes N tiny groups.
Yao Lu, Guangming Lu, Jinxing Li
exaly   +3 more sources