AI18 Generative Hints 논문: https://arxiv.org/abs/2511.02933 Generative HintsData augmentation is widely used in vision to introduce variation and mitigate overfitting, through enabling models to learn invariant properties, such as spatial invariance. However, these properties are not fully captured by data augmentation alone, sincarxiv.orgTitle: Generative HintsAuthors: Andy Dimnaku, Abdullah Yusuf Kavranoğlu, Yaser A.. 2025. 12. 16. Deep Residual Learning for Image Recognition 논문: https://arxiv.org/abs/1512.03385 Deep Residual Learning for Image RecognitionDeeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions witharxiv.orgTitle: Deep Residual Learning for Image RecognitionA.. 2025. 12. 12. CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features 정리 논문: https://arxiv.org/abs/1905.04899 CutMix: Regularization Strategy to Train Strong Classifiers with Localizable FeaturesRegional dropout strategies have been proposed to enhance the performance of convolutional neural network classifiers. They have proved to be effective for guiding the model to attend on less discriminative parts of objects (e.g. leg as opposed to head ofarxiv.orgTitle: CutMi.. 2025. 12. 12. What is YOLOV5: A Deep look into the internal features of the object detector 논문: https://arxiv.org/html/2407.20892v1 What is YOLOv5: A deep look into the internal features of the popular object detectorWhat is YOLOv5: A deep look into the internal features of the popular object detector Rahima Khanam* and Muhammad Hussain Department of Computer Science, Huddersfield University, Queensgate, Huddersfield HD1 3DH, UK; *Correspondence: rahima.khanam@hud.ac.uarxiv.orgTitleWha.. 2025. 9. 23. Distilling the Knowledge in a Neural Network 리뷰 논문: https://arxiv.org/abs/1503.02531 Distilling the Knowledge in a Neural NetworkA very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions. Unfortunately, making predictions using a whole ensemble of models is cumbersomearxiv.orgTitle: Distilling the Knowledge in a Neural NetworkA.. 2025. 9. 14. Exploring Better Food Detection via Transfer Learning 리뷰 논문: https://ieeexplore.ieee.org/document/8757886 Exploring Better Food Detection via Transfer LearningIn this paper, we present a food-specialized detection1 deep learning architecture with knowledge transferred from a pretrained food/non-food classification model. Existing approaches in object detection all separate it from image classification due to theieeexplore.ieee.orgTitle: Exploring Bett.. 2025. 9. 7. 이전 1 2 3 다음
