Related papers: CLARA: A Modular Framework for Unsupervised Transi…
Unsupervised learning visible-infrared person re-identification (USL-VI-ReID) aims to learn modality-invariant features from unlabeled cross-modality datasets and reduce the inter-modality gap. However, the existing methods lack…
We present a new method to detect planetary transits from time-series photometry, the Transit Least Squares (TLS) algorithm. TLS searches for transit-like features while taking the stellar limb darkening and planetary ingress and egress…
Vast amounts of astronomical photometric data are generated from various projects, requiring significant effort to identify variable stars and other object classes. In light of this, a general, widely applicable classification framework…
The ever-growing amount of sensor data from machines, smart devices, and the environment leads to an abundance of high-resolution, unannotated time series (TS). These recordings encode recognizable properties of latent states and…
Part feature learning is critical for fine-grained semantic understanding in vehicle re-identification. However, existing approaches directly model part features and global features, which can easily lead to serious gradient vanishing…
Time series anomaly detection is essential for the reliable operation of complex systems, but most existing methods require extensive task-specific training. We explore whether time series foundation models (TSFMs), pretrained on large…
Unsupervised domain adaptation (UDA) is to learn classification models that make predictions for unlabeled data on a target domain, given labeled data on a source domain whose distribution diverges from the target one. Mainstream UDA…
Visual Tracking is a complex problem due to unconstrained appearance variations and dynamic environment. Extraction of complementary information from the object environment via multiple features and adaption to the target's appearance…
Contrastive learning is a promising approach to unsupervised learning, as it inherits the advantages of well-studied deep models without a dedicated and complex model design. In this paper, based on bidirectional encoder representations…
The Transiting Exoplanet Survey Satellite (TESS) is continuing its second extended mission after 55 sectors of observations. TESS publishes full-frame images (FFI) at a cadence of 1800, 600, or 200 seconds, allowing light curves to be…
Unsupervised person re-identification (Re-ID) aims to match pedestrian images from different camera views in unsupervised setting. Existing methods for unsupervised person Re-ID are usually built upon the pseudo labels from clustering.…
In this paper, we propose a multiple object tracker, called MF-Tracker, that integrates multiple classical features (spatial distances and colours) and modern features (detection labels and re-identification features) in its tracking…
Sparse autoencoders (SAEs) decompose language model activations into interpretable features, but existing methods reveal only which features activate, not which change model outputs when amplified. We introduce Control Reinforcement…
Concept drift is the phenomenon in which the underlying data distributions and statistical properties of a target domain change over time, leading to a degradation in model performance. Consequently, production models require continuous…
Improving sample efficiency is a key research problem in reinforcement learning (RL), and CURL, which uses contrastive learning to extract high-level features from raw pixels of individual video frames, is an efficient…
Strong lensing in galaxy clusters probes properties of dense cores of dark matter halos in mass, studies the distant universe at flux levels and spatial resolutions otherwise unavailable, and constrains cosmological models independently.…
Supervised contour detection methods usually require many labeled training images to obtain satisfactory performance. However, a large set of annotated data might be unavailable or extremely labor intensive. In this paper, we investigate…
Recent approaches leveraging multi-modal pre-trained models like CLIP for Unsupervised Domain Adaptation (UDA) have shown significant promise in bridging domain gaps and improving generalization by utilizing rich semantic knowledge and…
Unsupervised Domain Adaptive (UDA) person search focuses on employing the model trained on a labeled source domain dataset to a target domain dataset without any additional annotations. Most effective UDA person search methods typically…
In this work, we present a framework for estimating and evaluating uncertainty in deep-attention-based classifiers for light curves for variable stars. We implemented three techniques, Deep Ensembles (DEs), Monte Carlo Dropout (MCD) and…