Automated learning rate search using batch-level cross-validation

Kabakcı, Duygu
Deep convolutional neural networks are being widely used in computer vision tasks, such as object recognition and detection, image segmentation and face recognition, with a variety of architectures. Deep learning researchers and practitioners have accumulated a significant amount of experience on training a wide variety of architectures on various datasets. However, given a specific network model and a dataset, obtaining the best model (i.e. the model giving the smallest test set error) while keeping the training time complexity low is still a challenging task. Hyper-parameters of deep neural networks, especially the learning rate and its (decay) schedule, highly affect the network’s final performance. The general approach is to search the best learning rate and learning rate decay parameters within a cross-validation framework, a process that usually requires a significant amount of experimentation with extensive time cost. In classical cross-validation, a random part of the dataset is reserved for the evaluation of model performance on unseen data. This technique is usually run multiple times to decide learning rate settings with random validation sets. This thesis is aimed at exploring batch-level cross-validation methods as an alternative to the v classical dataset-level, hence macro, CV. The advantage of micro CV methods is that the gradient computed during training is re-used to evaluate several different learning rates. We propose automated learning rate selection algorithms that are aimed to address setting the learning rate and learning rate schedule during training. Our algorithms use micro cross-validation where a random half of the current batch (of examples) is used for training and the other half is used for validation. We present comprehensive experimental results on three well-known datasets (CIFAR10, SVHN and ADIENCE) using three different network architectures: a custom CNN, ResNet and VGG.


Fine-Grained Object Recognition and Zero-Shot Learning in Remote Sensing Imagery
Sumbul, Gencer; Cinbiş, Ramazan Gökberk; Aksoy, Selim (2018-02-01)
Fine-grained object recognition that aims to identify the type of an object among a large number of subcategories is an emerging application with the increasing resolution that exposes new details in image data. Traditional fully supervised algorithms fail to handle this problem where there is low betweenclass variance and high within-class variance for the classes of interest with small sample sizes. We study an even more extreme scenario named zero-shot learning (ZSL) in which no training example exists f...
Visual Object Tracking with Autoencoder Representations
Besbinar, Beril; Alatan, Abdullah Aydın (2016-05-19)
Deep learning is the discipline of training computational models that are composed of multiple layers and these methods have recently improved the state of the art in many areas as a virtue of large labeled datasets, increase in the computational power of current hardware and unsupervised training methods. Although such a dataset may not be available for lots of application areas, the representations obtained by the well-designed networks that have a large representation capacity and trained with enough dat...
Perceptual quality preserving adversarial attacks
Aksoy, Bilgin; Temizel, Alptekin; Department of Modeling and Simulation (2019)
Deep learning is used in various succesful computer vision applications such as image classification. Deep neural networks (DNN) especially convolutional neural networks have reached above human level accuracy rates for image classification tasks. While DNNs have solved the image classification task and enabled its use in many practical applications, recent research has unveiled some properties which could degrade their performance. Adversarial images are samples that are intentionally modified by adding no...
Face Recognition Based on Embedding Learning
Karaman, Kaan; Koc, Aykut; Alatan, Abdullah Aydın (2018-09-11)
Face recognition is a key task of computer vision research that has been employed in various security and surveillance applications. Recently, the importance of this task has risen with the improvements in the quality of sensors of cameras, as well as with the increasing coverage of camera networks setup everywhere in the cities. Moreover, biometry-based technologies have been developed for the last three decades and have been available on many devices such as the mobile phones. The goal is to identify peop...
Deep Hierarchies in the Primate Visual Cortex: What Can We Learn for Computer Vision?
KRÜGER, Norbert; JANSSEN, Peter; Kalkan, Sinan; LAPPE, Markus; LEONARDİS, Ales; PİATER, Justus; Rodriguez-Sanchez, Antonio J.; WİSKOTT, Laurenz (Institute of Electrical and Electronics Engineers (IEEE), 2013-08-01)
Computational modeling of the primate visual system yields insights of potential relevance to some of the challenges that computer vision is facing, such as object recognition and categorization, motion detection and activity recognition, or vision-based navigation and manipulation. This paper reviews some functional principles and structures that are generally thought to underlie the primate visual cortex, and attempts to extract biological principles that could further advance computer vision research. Or...
Citation Formats
D. Kabakcı, “Automated learning rate search using batch-level cross-validation,” Thesis (M.S.) -- Graduate School of Natural and Applied Sciences. Computer Engineering., Middle East Technical University, 2019.