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
Classification of diffraction patterns using a convolutional neural network in single particle imaging experiments performed at X-ray free-electron lasers
Dameli Assalauova, Alexandr Ignatenko, Fabian Isensee, Sergey Bobkov, Darya Trofimova, Ivan A. Vartanyants
Classification Under Ambiguity: When Is Average-K Better Than Top-K?
Titouan Lorieul, Alexis Joly, Dennis Shasha
Sports Video: Fine-Grained Action Detection and Classification of Table Tennis Strokes from Videos for MediaEval 2021
Pierre-Etienne Martin, Jordan Calandre, Boris Mansencal, Jenny Benois-Pineau, Renaud Péteri, Laurent Mascarilla, Julien Morlier