Related papers: MODEL&CO: Exoplanet detection in angular different…
Material recognition for real-world outdoor surfaces has become increasingly important for computer vision to support its operation "in the wild." Computational surface modeling that underlies material recognition has transitioned from…
Deep-learning-based approaches for retinal lesion segmentation often require an abundant amount of precise pixel-wise annotated data. However, coarse annotations such as circles or ellipses for outlining the lesion area can be six times…
Anomaly detection with convolutional autoencoders is a popular method to search for new physics in a model-agnostic manner. These techniques are powerful, but they are still a "black box," since we do not know what high-level physical…
In this paper, we proposed to investigate unsupervised anomaly detection in Synthetic Aperture Radar (SAR) images. Our approach considers anomalies as abnormal patterns that deviate from their surroundings but without any prior knowledge of…
Recent progress in contrastive learning has revolutionized unsupervised representation learning. Concretely, multiple views (augmentations) from the same image are encouraged to map to the similar embeddings, while views from different…
Training deep object detectors requires significant amount of human-annotated images with accurate object labels and bounding box coordinates, which are extremely expensive to acquire. Noisy annotations are much more easily accessible, but…
Continual learning seeks to maintain stable adaptation under non-stationary environments, yet this problem becomes particularly challenging in object detection, where most existing methods implicitly assume relatively balanced visual…
Angular differential imaging provides a novel way of probing the high contrast of our universe. Until now, its applications have been primarily localized to searching for exoplanets around nearby stars. This work presents a suite of…
Clouds and other features in exoplanet and brown dwarf atmospheres cause variations in brightness as they rotate in and out of view. Ground-based instruments reach the high contrasts and small inner working angles needed to monitor these…
The direct detection of exoplanets with high-contrast instruments can be boosted with high spectral resolution. For integral field spectrographs yielding hyperspectral data, this means that the field of view consists of diffracted starlight…
We apply the Minimum Description Length model selection approach to the detection of extra-solar planets, and use this example to show how specification of the experimental design affects the prior distribution on the model parameter space…
CONTEXT: Combining high-contrast imaging with high-resolution spectroscopy offers a powerful way to detect and characterize exoplanets around nearby stars, despite challenges linked to their faintness. Instruments like VLT/SPHERE are state…
Compared with traditional machine learning models, deep neural networks perform better, especially in image classification tasks. However, they are vulnerable to adversarial examples. Adding small perturbations on examples causes a…
We present a neural point cloud rendering pipeline through a novel multi-frequency-aware patch adversarial learning framework. The proposed approach aims to improve the rendering realness by minimizing the spectrum discrepancy between real…
High-contrast imaging (HCI) is a technique designed to observe faint signals near bright sources, such as exoplanets and circumstellar disks. The primary challenge in revealing the faint circumstellar signal near a star is the presence of…
Supervised learning-based adversarial attack detection methods rely on a large number of labeled data and suffer significant performance degradation when applying the trained model to new domains. In this paper, we propose a self-supervised…
Although deep learning has been applied to successfully address many data mining problems, relatively limited work has been done on deep learning for anomaly detection. Existing deep anomaly detection methods, which focus on learning new…
Many real-world phenomena are observed at multiple resolutions. Predictive models designed to predict these phenomena typically consider different resolutions separately. This approach might be limiting in applications where predictions are…
Various technologies, including computer vision models, are employed for the automatic monitoring of manual assembly processes in production. These models detect and classify events such as the presence of components in an assembly area or…
Prototype-based reconstruction methods for unsupervised anomaly detection utilize a limited set of learnable prototypes which only aggregates insufficient normal information, resulting in undesirable reconstruction. However, increasing the…