Related papers: CLARA: A Modular Framework for Unsupervised Transi…
Many Click-Through Rate (CTR) prediction works focused on designing advanced architectures to model complex feature interactions but neglected the importance of feature representation learning, e.g., adopting a plain embedding layer for…
Multi-view unsupervised feature selection (MUFS), which selects informative features from multi-view unlabeled data, has attracted increasing research interest in recent years. Although great efforts have been devoted to MUFS, several…
Unsupervised image clustering methods often introduce alternative objectives to indirectly train the model and are subject to faulty predictions and overconfident results. To overcome these challenges, the current research proposes an…
We present a novel clustering objective that learns a neural network classifier from scratch, given only unlabelled data samples. The model discovers clusters that accurately match semantic classes, achieving state-of-the-art results in…
While modern deep neural networks achieve impressive performance in vision tasks, they remain opaque in their decision processes, risking unwarranted trust, undetected biases and unexpected failures. We propose cluster paths, a post-hoc…
The rise of AI-powered classification techniques has ushered in a new era for data-driven Fault Detection and Diagnosis in smart building systems. While extensive research has championed supervised FDD approaches, the real-world application…
Unsupervised domain adaptation (UDA) is to make predictions for unlabeled data on a target domain, given labeled data on a source domain whose distribution shifts from the target one. Mainstream UDA methods learn aligned features between…
Stellar flares are abundant in space photometric light curves. As they are now available in large enough numbers, the statistical study of their overall temporal morphology is timely. We use light curves from the Transiting Exoplanet Survey…
We developed, tested and validated a new Fast, Robust and Automated (FRA) tool to detect solar-like oscillations. FRA is based on the detection and measurement of the frequency of maximum oscillation power $\nu_{max}$, without relying on…
This paper investigates the frequency of transiting planetary systems around metal-polluted white dwarfs using high-cadence photometry from ULTRACAM and ULTRASPEC on the ground, and space-based observations with TESS. Within a sample of 313…
Semi-supervised learning has substantially advanced medical image segmentation since it alleviates the heavy burden of acquiring the costly expert-examined annotations. Especially, the consistency-based approaches have attracted more…
Asteroseismology provides a powerful probe of stellar interiors by detecting stellar oscillations, including solar-like oscillations, which are stochastically excited by near-surface convection. While thousands of solar-like oscillators…
Unsupervised clustering aims at discovering the semantic categories of data according to some distance measured in the representation space. However, different categories often overlap with each other in the representation space at the…
Self-Supervised Learning (SSL) enables us to pre-train foundation models without costly labeled data. Among SSL methods, Contrastive Learning (CL) methods are better at obtaining accurate semantic representations in noise interference.…
Clustering is ubiquitous in data analysis, including analysis of time series. It is inherently subjective: different users may prefer different clusterings for a particular dataset. Semi-supervised clustering addresses this by allowing the…
Low-rank adaptation (LoRA) has achieved remarkable success in fine-tuning pre-trained vision transformers for various downstream tasks. Existing studies mainly focus on exploring more parameter-efficient strategies or more effective…
As a fundamental data mining task, unsupervised time series anomaly detection (TSAD) aims to build a model for identifying abnormal timestamps without assuming the availability of annotations. A key challenge in unsupervised TSAD is that…
With inspiration from Random Forests (RF) in the context of classification, a new clustering ensemble method---Cluster Forests (CF) is proposed. Geometrically, CF randomly probes a high-dimensional data cloud to obtain "good local…
Blazars are characterized by largely aperiodic variability on timescales ranging from minutes to decades across the electromagnetic spectrum. The TESS (Transiting Exoplanet Survey Satellite) mission provides continuous sampling of blazar…
In recent years, a variety of contrastive learning based unsupervised visual representation learning methods have been designed and achieved great success in many visual tasks. Generally, these methods can be roughly classified into four…