Related papers: SUDS: A Strategy for Unsupervised Drift Sampling

Advanced Driver Assistance Systems (ADAS) have made significant strides, capitalizing on computer vision to enhance perception and decision-making capabilities. Nonetheless, the adaptation of these systems to diverse traffic scenarios poses…

Recently, transfer subspace learning based approaches have shown to be a valid alternative to unsupervised subspace clustering and temporal data clustering for human motion segmentation (HMS). These approaches leverage prior knowledge from…

We propose a novel domain adaptive action detection approach and a new adaptation protocol that leverages the recent advancements in image-level unsupervised domain adaptation (UDA) techniques and handle vagaries of instance-level video…

Unsupervised tabular anomaly detection methods typically learn feature patterns from normal samples during training and subsequently identify samples that deviate from these patterns as anomalies during testing. However, in practical…

Deep learning algorithms can fare poorly when the training dataset suffers from heavy class-imbalance but the testing criterion requires good generalization on less frequent classes. We design two novel methods to improve performance in…

Many real-world applications adopt multi-label data streams as the need for algorithms to deal with rapidly changing data increases. Changes in data distribution, also known as concept drift, cause the existing classification models to…

The performance of existing point cloud-based 3D object detection methods heavily relies on large-scale high-quality 3D annotations. However, such annotations are often tedious and expensive to collect. Semi-supervised learning is a good…

Nowadays, Machine Learning and Deep Learning methods have become the state-of-the-art approach to solve data classification tasks. In order to use those methods, it is necessary to acquire and label a considerable amount of data; however,…

Machine learning based malware detectors become obsolete over time due to concept drift in benign and malware applications. Recent methods rely on fully labeled data and use hierarchical contrastive loss (HCL) with active learning to…

Semi-Supervised Learning (SSL) is important for reducing the annotation cost for medical image segmentation models. State-of-the-art SSL methods such as Mean Teacher, FixMatch and Cross Pseudo Supervision (CPS) are mainly based on…

Anomaly detection aims to distinguish abnormal instances that deviate significantly from the majority of benign ones. As instances that appear in the real world are naturally connected and can be represented with graphs, graph neural…

Machine learning-based Android malware classifiers achieve high accuracy in stationary environments but struggle with concept drift. The rapid evolution of malware, especially with new families, can depress classification accuracy to…

Pre-trained models exhibit strong generalization to various downstream tasks. However, given the numerous models available in the model hub, identifying the most suitable one by individually fine-tuning is time-consuming. In this paper, we…

Machine Unlearning is essential for large generative models (VAEs, DDPMs) to comply with the right to be forgotten and prevent undesired content generation without costly retraining. Existing approaches, such as Static-lambda SISS for…

Relational database management systems (RDBMS) are widely used for the storage of structured data. To derive insights beyond statistical aggregation, we typically have to extract specific subdatasets from the database using conventional…

The limited and dynamically varied resources on edge devices motivate us to deploy an optimized deep neural network that can adapt its sub-networks to fit in different resource constraints. However, existing works often build sub-networks…

Concept drift and label scarcity are two critical challenges limiting the robustness of predictive models in dynamic industrial environments. Existing drift detection methods often assume global shifts and rely on dense supervision, making…

Given data with label noise (i.e., incorrect data), deep neural networks would gradually memorize the label noise and impair model performance. To relieve this issue, curriculum learning is proposed to improve model performance and…

Recent Semi-Supervised Object Detection (SS-OD) methods are mainly based on self-training, i.e., generating hard pseudo-labels by a teacher model on unlabeled data as supervisory signals. Although they achieved certain success, the limited…

Detecting and labeling stance in social media text is strongly motivated by hate speech detection, poll prediction, engagement forecasting, and concerted propaganda detection. Today's best neural stance detectors need large volumes of…