Related papers: Prototype-oriented Unsupervised Change Detection f…

Deploying 3D detectors in unfamiliar domains has been demonstrated to result in a significant 70-90% drop in detection rate due to variations in lidar, geography, or weather from their training dataset. This domain gap leads to missing…

Out-of-distribution (OOD) detection is a crucial task for ensuring the reliability and safety of deep learning. Currently, discriminator models outperform other methods in this regard. However, the feature extraction process used by…

Motivated by Industry 4.0 applications, we consider quickest change detection (QCD) of an abrupt change in a process when its measurements are transmitted by a sensor over a lossy wireless link to a decision maker (DM). The sensor node…

Radar must adapt to changing environments, and we propose changepoint detection as a method to do so. In the world of increasingly congested radio frequencies, radars must adapt to avoid interference. Many radar systems employ the…

In daily life and industrial production, it is crucial to accurately detect changes in liquid level in containers. Traditional contact measurement methods have some limitations, while emerging non-contact image processing technology shows…

The field of Remote Sensing (RS) widely employs Change Detection (CD) on very-high-resolution (VHR) images. A majority of extant deep-learning-based methods hinge on annotated samples to complete the CD process. Recently, the emergence of…

Existing 3D object detectors encounter extreme challenges in localizing unseen 3D objects and recognizing them as unseen, which is a crucial technology in autonomous driving in the wild. To address these challenges, we propose practical…

In Continual Learning (CL) contexts, concept drift typically refers to the analysis of changes in data distribution. A drift in the input data can have negative consequences on a learning predictor and the system's stability. The majority…

Semantic change detection in remote sensing aims to identify land cover changes between bi-temporal image pairs. Progress in this area has been limited by the scarcity of annotated datasets, as pixel-level annotation is costly and…

Most unsupervised domain adaptation (UDA) methods assume that labeled source images are available during model adaptation. However, this assumption is often infeasible owing to confidentiality issues or memory constraints on mobile devices.…

Supervised machine learning often encounters concept drift, where the data distribution changes over time, degrading model performance. Existing drift detection methods focus on identifying these shifts but often overlook the challenge of…

Universal Cross-Domain Retrieval (UCDR) retrieves relevant images from unseen domains and classes without semantic labels, ensuring robust generalization. Existing methods commonly employ prompt tuning with pre-trained vision-language…

While modern deep learning methods have shown great promise in the problem of earthquake detection, the most successful methods so far have been based on supervised learning, which requires large datasets with ground-truth labels. The…

Unsupervised Domain Adaptation (UDA) transfers predictive models from a fully-labeled source domain to an unlabeled target domain. In some applications, however, it is expensive even to collect labels in the source domain, making most…

Real-world machine learning applications often face simultaneous covariate and semantic shifts, challenging traditional domain generalization and out-of-distribution (OOD) detection methods. We introduce Meta-learned Across Domain…

We present different methods of unsupervised learning which can be used for outlier detection in high energy nuclear collisions. The UrQMD model is used to generate the bulk background of events as well as different variants of outlier…

This work tackles the unsupervised cross-domain object detection problem which aims to generalize a pre-trained object detector to a new target domain without labels. We propose an uncertainty-aware model adaptation method, which is based…

Change Detection (CD) enables the identification of alterations between images of the same area captured at different times. However, existing CD methods still struggle to address pseudo changes resulting from domain information differences…

Material Fingerprinting is a lookup table-based strategy to discover material models from experimental measurements, which completely avoids the need to solve an optimization problem. In an offline phase, a comprehensive database of…

Recent studies show that using potential out-of-distribution (OOD) labels from large corpora as auxiliary information can improve OOD detection in vision-language models (VLMs). However, these methods often fail when real-world OOD samples…