Related papers: AggSS: An Aggregated Self-Supervised Approach for …

Image augmentation techniques apply transformation functions such as rotation, shearing, or color distortion on an input image. These augmentations were proven useful in improving neural networks' generalization ability. In this paper, we…

Intrusion detection systems (IDSs) play an important role in identifying malicious attacks and threats in networking systems. As fundamental tools of IDSs, learning based classification methods have been widely employed. When it comes to…

In this paper we propose to augment a modern neural-network architecture with an attention model inspired by human perception. Specifically, we adversarially train and analyze a neural model incorporating a human inspired, visual attention…

Neural networks have become increasingly popular in the last few years as an effective tool for the task of image classification due to the impressive performance they have achieved on this task. In image classification tasks, it is common…

In contrastive self-supervised learning, the common way to learn discriminative representation is to pull different augmented "views" of the same image closer while pushing all other images further apart, which has been proven to be…

Improving the performance on an imbalanced training set is one of the main challenges in nowadays Machine Learning. One way to augment and thus re-balance the image dataset is through existing deep generative models, like class-conditional…

Deep convolutional neural network (DCNN) based supervised learning is a widely practiced approach for large-scale image classification. However, retraining these large networks to accommodate new, previously unseen data demands high…

Industrial image anomaly detection under the setting of one-class classification has significant practical value. However, most existing models struggle to extract separable feature representations when performing feature embedding and…

Deep neural networks need a big amount of training data, while in the real world there is a scarcity of data available for training purposes. To resolve this issue unsupervised methods are used for training with limited data. In this…

In the context of mobile sensing environments, various sensors on mobile devices continually generate a vast amount of data. Analyzing this ever-increasing data presents several challenges, including limited access to annotated data and a…

Recently, the growing capabilities of deep generative models have underscored their potential in enhancing image classification accuracy. However, existing methods often demand the generation of a disproportionately large number of images…

Self-supervised learning is a popular and powerful method for utilizing large amounts of unlabeled data, for which a wide variety of training objectives have been proposed in the literature. In this study, we perform a Bayesian analysis of…

In statistical modelling the biggest threat is concept drift which makes the model gradually showing deteriorating performance over time. There are state of the art methodologies to detect the impact of concept drift, however general…

In self-supervised representation learning, a common idea behind most of the state-of-the-art approaches is to enforce the robustness of the representations to predefined augmentations. A potential issue of this idea is the existence of…

This paper introduces a novel approach to improving the training stability of self-supervised learning (SSL) methods by leveraging a non-parametric memory of seen concepts. The proposed method involves augmenting a neural network with a…

Deep learning models suffer from catastrophic forgetting when learning new tasks incrementally. Incremental learning has been proposed to retain the knowledge of old classes while learning to identify new classes. A typical approach is to…

As neural networks are increasingly being applied to real-world applications, mechanisms to address distributional shift and sequential task learning without forgetting are critical. Methods incorporating network expansion have shown…

Modern consumer cameras commonly employ the rolling shutter (RS) imaging mechanism, via which images are captured by scanning scenes row-by-row, resulting in RS distortion for dynamic scenes. To correct RS distortion, existing methods adopt…

This paper introduces an active learning framework for manifold Gaussian Process (GP) regression, combining manifold learning with strategic data selection to improve accuracy in high-dimensional spaces. Our method jointly optimizes a…

Modern consumer cameras usually employ the rolling shutter (RS) mechanism, where images are captured by scanning scenes row-by-row, yielding RS distortions for dynamic scenes. To correct RS distortions, existing methods adopt a fully…