相关论文: Do we still need ImageNet pre-training in remote s…

Contrastive self-supervised learning has largely narrowed the gap to supervised pre-training on ImageNet. However, its success highly relies on the object-centric priors of ImageNet, i.e., different augmented views of the same image…

Self-supervised learning (SSL) methods have become a dominant paradigm for creating general purpose models whose capabilities can be transferred to downstream supervised learning tasks. However, most such methods rely on vast amounts of…

Image classification is one of the main drivers of the rapid developments in deep learning with convolutional neural networks for computer vision. So is the analogous task of scene classification in remote sensing. However, in contrast to…

Supervised machine learning provides state-of-the-art solutions to a wide range of computer vision problems. However, the need for copious labelled training data limits the capabilities of these algorithms in scenarios where such input is…

Visual localization is critical to many applications in computer vision and robotics. To address single-image RGB localization, state-of-the-art feature-based methods match local descriptors between a query image and a pre-built 3D model.…

This study aims to optimize the few-shot image classification task and improve the model's feature extraction and classification performance by combining self-supervised learning with the deep network model ResNet-101. During the training…

This paper investigates the impact of sampling and pretraining using datasets with different image characteristics on the performance of self-supervised learning (SSL) models for object classification. To do this, we sample two apartment…

Unsupervised learning has always been appealing to machine learning researchers and practitioners, allowing them to avoid an expensive and complicated process of labeling the data. However, unsupervised learning of complex data is…

Transferring the weights of a pre-trained model to assist another task has become a crucial part of modern deep learning, particularly in data-scarce scenarios. Pre-training refers to the initial step of training models outside the current…

Semantic segmentation networks are usually pre-trained once and not updated during deployment. As a consequence, misclassifications commonly occur if the distribution of the training data deviates from the one encountered during the robot's…

Deep neural networks produce state-of-the-art results when trained on a large number of labeled examples but tend to overfit when small amounts of labeled examples are used for training. Creating a large number of labeled examples requires…

Recent algorithms with state-of-the-art few-shot classification results start their procedure by computing data features output by a large pretrained model. In this paper we systematically investigate which models provide the best…

This work presents a multitemporal class-driven hierarchical Residual Neural Network (ResNet) designed for modelling the classification of Time Series (TS) of multispectral images at different semantical class levels. The architecture…

It is an open secret that ImageNet is treated as the panacea of pretraining. Particularly in medical machine learning, models not trained from scratch are often finetuned based on ImageNet-pretrained models. We posit that pretraining on…

The fast development of self-supervised learning lowers the bar learning feature representation from massive unlabeled data and has triggered a series of research on change detection of remote sensing images. Challenges in adapting…

The mining and utilization of features directly affect the classification performance of models used in the classification and recognition of hyperspectral remote sensing images. Traditional models usually conduct feature mining from a…

In recent years, self-supervised learning has attracted widespread academic debate and addressed many of the key issues of computer vision. The present research focus is on how to construct a good agent task that allows for improved network…

Parameter fine tuning is a transfer learning approach whereby learned parameters from pre-trained source network are transferred to the target network followed by fine-tuning. Prior research has shown that this approach is capable of…

Deep neural networks are typically trained under a supervised learning framework where a model learns a single task using labeled data. Instead of relying solely on labeled data, practitioners can harness unlabeled or related data to…

Automatically finding good and general remote sensing representations allows to perform transfer learning on a wide range of applications - improving the accuracy and reducing the required number of training samples. This paper investigates…