Evaluating histopathology foundation models for few-shot tissue clustering: an application to LC25000 augmented dataset cleaning by Batchkala, G, Li, B, Rittscher, J

“…Our contributions are: 1) We publicly release our semiautomatic annotation pipeline along with the LC25000-clean dataset to facilitate appropriate utilization of this dataset, reducing the risk of overestimating models’ performance; 2) We profile various combinations of feature extraction and clustering methods for identifying duplicates of the same image generated by basic image transformations; 3) We propose the clustering task as a minimal-setup benchmark to evaluate the quality of tissue image features learned by histopathology foundation models. Clustering labels, annotation pipeline, and evaluation code: https://github.com/GeorgeBatch/LC25000-clean…”

A Feature-Oriented Reconstruction Method for Surface-Defect Detection on Aluminum Profiles by Shancheng Tang, Ying Zhang, Zicheng Jin, Jianhui Lu, Heng Li, Jiqing Yang

“…The aluminum profile image preprocessing stage uses techniques such as boundary extraction, background removal, and data normalization to process the original image and extract the image of the main part of the aluminum profile, which reduces the influence of irrelevant data features on the algorithm. The essential features learning stage precedes the feature-optimization module to eliminate the texture interference of the irregular distribution of the aluminum profile surface, and image blocks of the area images are reconstructed one by one to extract the features through the mask. …”
Get full text

Multi-Task Time Series Forecasting Based on Graph Neural Networks by Xiao Han, Yongjie Huang, Zhisong Pan, Wei Li, Yahao Hu, Gengyou Lin

“…In time series forecasting tasks, the features learned by a specific task at the current time step (such as predicting mortality) are related to the features of historical timesteps and the features of adjacent timesteps of related tasks (such as predicting fever). …”
Get full text

Trainable Weights for Multitask Learning by Chaeeun Ryu, Changwoo Lee, Hyuk Jin Choi, Chang-Hyun Lee, Byoungjun Jeon, Eui Kyu Chie, Young-Gon Kim

“…This work underscores that by simply learning weights to better order the features learned by a single backbone, we can incur better task-specific performance of the model.…”
Get full text

Deep learning-based multimodality classification of chronic mild traumatic brain injury using resting-state functional MRI and PET imaging by Faezeh Vedaei, Najmeh Mashhadi, Mahdi Alizadeh, George Zabrecky, Daniel Monti, Nancy Wintering, Emily Navarreto, Chloe Hriso, Andrew B. Newberg, Andrew B. Newberg, Feroze B. Mohamed

“…Additionally, a novel data interpretation approach was utilized to identify top-performing features learned by the AEs. Our method delivered a classification accuracy within the range of 79–91.67% for single neuroimaging modalities. …”
Get full text

An Embeddable Algorithm for Automatic Garbage Detection Based on Complex Marine Environment by Hongjie Deng, Daji Ergu, Fangyao Liu, Bo Ma, Ying Cai

“…Secondly, the spatial-channel attention mechanism is used to make features learn adaptively. It can effectively focus attention on detection objects. …”
Get full text

Date Fruit Sorting Based on Deep Learning and Discriminant Correlation Analysis by Oussama Aiadi, Belal Khaldi, Mohammed Lamine Kherfi, Mohamed Lamine Mekhalfi, Abdullah Alharbi

“…Specifically, we use discriminant correlation analysis (DCA) algorithm to fuse features learned from convolution neural networks (VGG-F) and an unsupervised network called PCANet. …”
Get full text

Prediction of exchangeable potassium in soil through mid-infrared spectroscopy and deep learning: From prediction to explainability by Franck Albinet, Yi Peng, Tetsuya Eguchi, Erik Smolders, Gerd Dercon

“…Used in the context of the implemented CNN on various Soil Taxonomy Orders, it allowed (i) to relate the important spectral features to domain knowledge and (ii) to demonstrate that including all Soil Taxonomy Orders in CNN-based modeling is beneficial as spectral features learned can be reused across different, sometimes underrepresented orders.…”
Get full text

Precipitation Retrieval From Fengyun-3D MWHTS and MWRI Data Using Deep Learning by Kangwen Liu, Jieying He, Haonan Chen

“…Nevertheless, it is still a challenge to extend the application of these models, which demands extracting the features learned from a certain area to other areas characterized by different precipitation features. …”
Get full text

Manipulation of Spatial Infrared Emission Based on W‐Doped Vanadium Oxide Films toward Thermal Coding by Laihao Lou, Tongtong Kang, Maoren Wang, Wenxin Li, Lei Bi, Li Zhang, Longjiang Deng, Peiheng Zhou

“…On the other hand, the concept of digital coding allows a high degree of freedom in manipulating the interacting physical quantities based on local discretized features. Learning from this idea, this study put forward the manipulation of spatial infrared emission based on tungsten (W)‐doped VO2 films toward thermal coding. …”
Get full text

Compact Cloud Detection with Bidirectional Self-Attention Knowledge Distillation by Yajie Chai, Kun Fu, Xian Sun, Wenhui Diao, Zhiyuan Yan, Yingchao Feng, Lei Wang

“…With bidirectional layer-wise features learning, the model can get a better representation of the cloud’s textural information and semantic information, so that the cloud’s boundaries become more detailed and the predictions become more reliable. …”
Get full text

NCA-Net for Tracking Multiple Objects across Multiple Cameras by Yihua Tan, Yuan Tai, Shengzhou Xiong

“…The network combines features learning and metric learning via a Convolutional Neural Network (CNN) model and the loss function similar to neighborhood components analysis (NCA). …”
Get full text

Lightweight Knowledge Distillation-Based Transfer Learning Framework for Rolling Bearing Fault Diagnosis by Ruijia Lu, Shuzhi Liu, Zisu Gong, Chengcheng Xu, Zonghe Ma, Yiqi Zhong, Baojian Li

“…Subsequently, a knowledge distillation framework incorporating a temperature factor is established to transfer fault features learned by the large teacher model in the source domain to the smaller student model, thereby reducing computational and parameter overhead. …”
Get full text

Infrared Fault Classification Based on the Siamese Network by Lili Zhang, Xiuhui Wang, Qifu Bao, Bo Jia, Xuesheng Li, Yaru Wang

“…Secondly, the images of the samples are input into the feature model combining convolution, adaptive coordinate attention (ACA), and the feature fusion module (FFM) to extract features, learning the similarities between different types of solar panel samples. …”
Get full text

Assessing chemistry teachers’ needs and expectations from integrated STEM education professional developments by Elif Selcan Oztay, Sevgi Aydin Gunbatar, Betul Ekiz Kiran

“…Additionally, the participants highlighted their expectations from a PD design to learn what integrated STEM education is and its essential features. Learning how to integrate STEM activities into lessons, developing integrated STEM lesson plans, and interdisciplinary chemistry teaching were other participants' expectations. …”
Get full text

Transductive meta-learning with enhanced feature ensemble for few-shot semantic segmentation by Amin Karimi, Charalambos Poullis

“…First, we present a novel ensemble of visual features learned from pretrained classification and semantic segmentation networks with the same architecture. …”
Get full text

A Deep Transfer Learning-Based Network for Diagnosing Minor Faults in the Production of Wireless Chargers by Yuping Wang, Weidong Li, Honghui Zhu

“…Finally, range adaptation using the maximum mean discrepancy between the features learned from the source and target ranges is realised by a multi-layer adaptive technology. …”
Get full text

Hard Negative Samples Contrastive Learning for Remaining Useful-Life Prediction of Bearings by Juan Xu, Lei Qian, Weiwei Chen, Xu Ding

“…Furthermore, to avoid the subtle variability of vibration data in the health stage to aggravate the degradation features learning of the model, we propose the hard negative samples by cosine similarity, which are most similar to the positive sample. …”
Get full text

A Self-Attention Model for Next Location Prediction Based on Semantic Mining by Eric Hsueh-Chan Lu, You-Ru Lin

“…In order to better perceive the trajectory, temporal features learn the periodicity of time series by the sine function. …”
Get full text

Lightweight Football Motion Recognition and Intensity Analysis Using Low-Cost Wearable Sensors by Qian Xie, Ning Jin, Shanshan Lu

“…Model validation is performed using three publicly available datasets, and the features learning strategies are analyzed. Finally, experiments are conducted on the collected football motion datasets and the experimental results show that the designed multitask model can perform two tasks simultaneously and can achieve high computational efficiency. …”
Get full text