Classification Code
Classification code research focuses on developing and improving algorithms and models to accurately assign data points to predefined categories. Current efforts concentrate on addressing challenges like imbalanced datasets, noisy data, and limited labeled data through techniques such as self-supervised pre-training, robust loss functions, and the application of diverse architectures including convolutional neural networks (CNNs), transformers, and novel approaches like Mamba. These advancements have significant implications across various fields, improving accuracy and efficiency in applications ranging from medical image analysis and bioacoustic monitoring to cybersecurity threat detection and scientific literature organization.
Papers
A multi-stream convolutional neural network for classification of progressive MCI in Alzheimer's disease using structural MRI images
Mona Ashtari-Majlan, Abbas Seifi, Mohammad Mahdi Dehshibi
Color Space-based HoVer-Net for Nuclei Instance Segmentation and Classification
Hussam Azzuni, Muhammad Ridzuan, Min Xu, Mohammad Yaqub
Nuclei instance segmentation and classification in histopathology images with StarDist
Martin Weigert, Uwe Schmidt
On classification of strategic agents who can both game and improve
Saba Ahmadi, Hedyeh Beyhaghi, Avrim Blum, Keziah Naggita
One Model is All You Need: Multi-Task Learning Enables Simultaneous Histology Image Segmentation and Classification
Simon Graham, Quoc Dang Vu, Mostafa Jahanifar, Shan E Ahmed Raza, Fayyaz Minhas, David Snead, Nasir Rajpoot
Functional mixture-of-experts for classification
Nhat Thien Pham, Faicel Chamroukhi
ConvNeXt-backbone HoVerNet for nuclei segmentation and classification
Jiachen Li, Chixin Wang, Banban Huang, Zekun Zhou
Recurrent Spectral Network (RSN): shaping the basin of attraction of a discrete map to reach automated classification
Lorenzo Chicchi, Duccio Fanelli, Lorenzo Giambagli, Lorenzo Buffoni, Timoteo Carletti
A new perspective on classification: optimally allocating limited resources to uncertain tasks
Toon Vanderschueren, Bart Baesens, Tim Verdonck, Wouter Verbeke