Nowadays deep learning-based methods have achieved a remarkable progress at the image classification task among a wide range of commonly used datasets (ImageNet, CIFAR, SVHN, Caltech 101, SUN397, etc.). SOTA performance on each of the mentioned datasets is obtained by careful tuning of the model architecture and training tricks according to the properties of the target data. Although this approach allows setting academic records, it is unrealistic that an average data scientist would have enough resources to build a sophisticated training pipeline for every image classification task he meets in practice. This work is focusing on reviewing the latest augmentation and regularization methods for the image classification and exploring ways to automatically choose some of the most important hyperparameters: total number of epochs, initial learning rate value and it's schedule. Having a training procedure equipped with a lightweight modern CNN architecture (like bileNetV3 or EfficientNet), sufficient level of regularization and adaptive to data learning rate schedule, we can achieve a reasonable performance on a variety of downstream image classification tasks without manual tuning of parameters to each particular task. Resulting models are computationally efficient and can be deployed to CPU using the OpenVINO toolkit. Source code is available as a part of the OpenVINO Training Extensions (https://github.com/openvinotoolkit/training_extensions).
Unsupervised Detection of Entry and Exit Regions from Vehicle Trajectories for Camera-Agnostic Turning Movement Counts
Robert Bosch Centre for Cyber-Physical Systems (RBCCPS), Centre for infrastructure, Sustainable Transportation and Urban Planning (CiSTUP)（罗伯特·博世网络物理系统中心（RBCCPS），基础设施、可持续交通与城市规划中心（CiSTUP））；Indian Institute of Science (IISc)（印度科学研究所）
Model Agnostic Preference Optimization for Medical Image Segmentation
DGIST, School of Undergrad Studies（DGIST研究生院）；DGIST, Department of Robotics and Mechatronics Engineering（DGIST机器人与机电工程系）；DGIST, Division of Intelligent Robot（DGIST智能机器人系）
MAO: Efficient Model-Agnostic Optimization of Prompt Tuning for Vision-Language Models
School of Mechanical Engineering and Automation, Shanghai University（上海大学机械工程与自动化学院）；Australian Artificial Intelligence Institute, University of Technology Sydney（悉尼科技大学澳大利亚人工智能学院）
AnyPos: Automated Task-Agnostic Actions for Bimanual Manipulation
Dept. of Comp. Sci. and Tech.（计算机科学与技术系）；Institute for AI（人工智能研究院）；BNRist Center（BNRist中心）；THBI Lab（THBI实验室）；Tsinghua-Bosch Joint ML Center（清华大学-博世联合机器学习中心）；Tsinghua University（清华大学）
MalariAI: A Label-Resilient Decoupled Framework for Annotation-Agnostic Cell Segmentation and Explainable Stage Classification in Dense Malaria Blood Smears
