A Single Image Deraining Algorithm Based on Swin Transformer by GAO Tao, WEN Yuanbo, CHEN Ting, ZHANG Jing

“…The latter uses Swin Transformer to capture the global information and long-distance dependencies between different pixels, in combination with residual convolution and dense connection to strengthen features learning. Finally, the derained image is obtained through a global residual convolution. …”
Get full text

Linear Time Non-Local Cost Aggregation on Complementary Spatial Tree Structures by Penghui Bu, Hang Wang, Yihua Dou, Hong Zhao

“…Moreover, a comparison of handcrafted features and deep features learned by convolutional neural networks (CNNs) in calculating the matching cost is also provided. …”
Get full text

Progressive Deep Learning Framework for Recognizing 3D Orientations and Object Class Based on Point Cloud Representation by Sukhan Lee, Yongjun Yang

“…The four independent networks are linked by in-between association subnetworks that are trained to progressively map the global features learned by individual networks one after another for fine-tuning the independent networks. …”
Get full text

A Combined Model of Diffusion Model and Enhanced Residual Network for Super-Resolution Reconstruction of Turbulent Flows by Jiaheng Qi, Hongbing Ma

“…This modification ensures the preservation of essential features learned by the SR3, while simultaneously enhancing the accuracy of the flow field. …”
Get full text

Genetic Programming-Based Machine Degradation Modeling Methodology by Tongtong Yan, Dong Wang

“…Aiming at solving this problem and visualizing informative features learned from degradation data, in this paper, a generalized machine degradation modeling methodology is proposed by integrating multiple-source fusion with genetic programming (GP). …”
Get full text

Medical text classification based on the discriminative pre-training model and prompt-tuning by Yu Wang, Yuan Wang, Zhenwan Peng, Feifan Zhang, Luyao Zhou, Fei Yang

“…The main idea of prompt-tuning is to transform binary or multi-classification tasks into mask prediction tasks by fully exploiting the features learned by pre-training language models. This study explores, for the first time, how to classify medical texts using a discriminative pre-training language model called ERNIE-Health through prompt-tuning. …”
Get full text

MCSNet: A Radio Frequency Interference Suppression Network for Spaceborne SAR Images via Multi-Dimensional Feature Transform by Xiuhe Li, Jinhe Ran, Hao Zhang, Shunjun Wei

“…To remove these RFI features presented on spaceborne SAR images, we propose a multi-dimensional calibration and suppression network (MCSNet) to exploit the features learning of spaceborne SAR images and RFI. In the scheme, a joint model consisting of the spaceborne SAR image and RFI is established based on the relationship between SAR echo and the scattering matrix. …”
Get full text

EDFA: Ensemble deep CNN for assessing student's cognitive state in adaptive online learning environments by Swadha Gupta, Parteek Kumar, RajKumar Tekchandani

“…The ensemble models have been created by applying transfer learning to two popular pre-trained models, VGG19 and ResNet50, which can learn useful features from facial images for emotion recognition tasks. Combining the features learned by both models, the ensemble approach can achieve better performance in recognising facial emotions. …”
Get full text

Infrared Target Detection Based on Interval Sampling Weighting and 3D Attention Head in Complex Scenario by Jimin Yu, Hui Wang, Shangbo Zhou, Shun Li

“…Furthermore, to our model, we introduce the C2f module to transfer gradient information across multiple branches. The features learned using diverse branches interact and fuse in subsequent stages, further enhancing the model’s representation ability and understanding of the target. …”
Get full text

Prominent features for generation Z learning behaviour in digital society environment by Farid, Nazatul Nabila

“…The analysis of prominent learning behaviour generation z with digital society environment is shown by a mapping of prominent learning behaviour generation z in digital society environment and discussion relates features learning behaviour is also being discussed.…”
Get full text

Comparative Evaluation of Non-Intrusive Load Monitoring Methods Using Relevant Features and Transfer Learning by Sarra Houidi, Dominique Fourer, François Auger, Houda Ben Attia Sethom, Laurence Miègeville

“…Finally, we introduce new transfer learning results, which confirm the relevance and the robustness of the selected features learned from our proposed dataset when they are transferred to a larger dataset. …”
Get full text

INTER-REGION TRANSFER LEARNING FOR LAND USE LAND COVER CLASSIFICATION by J. Siddamsetty, M. Stricker, M. Stricker, M. Charfuelan, M. Nuske, A. Dengel, A. Dengel

“…However, there are some open questions: to what extent can the features learned in one region be transferred to another? …”
Get full text

An overview of artificial intelligence in diabetic retinopathy and other ocular diseases by Bin Sheng, Bin Sheng, Xiaosi Chen, Xiaosi Chen, Tingyao Li, Tingyao Li, Tianxing Ma, Yang Yang, Yang Yang, Lei Bi, Xinyuan Zhang, Xinyuan Zhang

“…The Inception-v3 algorithm and transfer learning concept have been applied in DR and ARMD to reuse fundus image features learned from natural images (non-medical images) to train an AI system with a fraction of the commonly used training data (<1%). …”
Get full text

A Lightweight Real-Time Rice Blast Disease Segmentation Method Based on DFFANet by Changguang Feng, Minlan Jiang, Qi Huang, Lingguo Zeng, Changjiang Zhang, Yulong Fan

“…To realize the extraction of the shallow and deep features of rice blast disease as complete as possible, a feature extraction (DCABlock) module and a feature fusion (FFM) module are designed; then, a lightweight attention module is further designed to guide the features learning, effectively fusing the extracted features at different scales, and use the above modules to build a DFFANet lightweight network model. …”
Get full text

AFCANet: An adaptive feature concatenate attention network for multi-focus image fusion by Shuaiqi Liu, Weijian Peng, Yali Liu, Jie Zhao, Yonggang Su, Yudong Zhang

“…In the inference stage, we apply the pixel-based spatial frequency fusion rules to fuse the adaptive features learned by the encoder, which can successfully combine the texture and semantic information of the image and produce a more precise decision map. …”
Get full text

MyQuran diary application development considering the proposed usability features. by Maarop, Nurazean, Mohammad, Roslina, Jamaludin, Rosmahaida, Mohd. Zainuddin, Norziha Megat, Masrom, Maslin, Nik Mohamed, Nik Nadzirah, Abu Bakar, Nur Azaliah

“…This study also proposes usability aspects entailing usability features, learning and engagement qualities and Islamic genre application qualities. …”
Get full text

Detecting Errors with Zero-Shot Learning by Xiaoyu Wu, Ning Wang

“…Due to the inadequate sampling of negative samples, the features learned by those methods may be biased. In this paper, we propose an AEGAN (Auto-Encoder Generative Adversarial Network)-based deep learning model named SAT-GAN (Self-Attention Generative Adversarial Network) to detect errors in relational datasets. …”
Get full text

xViTCOS: Explainable Vision Transformer Based COVID-19 Screening Using Radiography by Arnab Kumar Mondal, Arnab Bhattacharjee, Parag Singla, A. P. Prathosh

“…Furthermore, we show that the features learned by our transformer networks are explainable. …”
Get full text

Identifying cancer driver genes based on multi-view heterogeneous graph convolutional network and self-attention mechanism by Wei Peng, Rong Wu, Wei Dai, Ning Yu

“…Meanwhile, we combined the fused features, the original features and the three features learned from every network through a logistic regression model to predict cancer driver genes. …”
Get full text

High Frequency Component Enhancement Network for Image Manipulation Detection by Wenyan Pan, Wentao Ma, Xiaoqian Wu, Wei Liu

“…The main stream branch takes the RGB image as input, and aggregates the features learned from the HFAB by the proposed multi-layer fusion (MLF) in a hierarchical manner. …”
Get full text