Related papers: How to Find More Supernovae with Less Work: Object…

In the upcoming decade large astronomical surveys will discover millions of transients raising unprecedented data challenges in the process. Only the use of the machine learning algorithms can process such large data volumes. Most of the…

This paper proposes a new approach for the selection of low-energy neutrino bursts, such as the ones detected after a supernova. It exploits the temporal structure of the expected signal with respect to the more diffuse background by…

Conventional training of deep neural networks requires a large number of the annotated image which is a laborious and time-consuming task, particularly for rare objects. Few-shot object detection (FSOD) methods offer a remedy by realizing…

Humans are able to learn to recognize new objects even from a few examples. In contrast, training deep-learning-based object detectors requires huge amounts of annotated data. To avoid the need to acquire and annotate these huge amounts of…

Modern machine learning tools offer exciting possibilities to qualitatively change the paradigm for new particle searches. In particular, new methods can broaden the search program by gaining sensitivity to unforeseen scenarios by learning…

Object pose estimation is important for object manipulation and scene understanding. In order to improve the general applicability of pose estimators, recent research focuses on providing estimates for novel objects, that is objects unseen…

Image set recognition has been widely applied in many practical problems like real-time video retrieval and image caption tasks. Due to its superior performance, it has grown into a significant topic in recent years. However, images with…

To avoid the exhaustive search over locations and scales, current state-of-the-art object detection systems usually involve a crucial component generating a batch of candidate object proposals from images. In this paper, we present a simple…

We consider the problem of object recognition in 3D using an ensemble of attribute-based classifiers. We propose two new concepts to improve classification in practical situations, and show their implementation in an approach implemented…

Supernovae classes have been defined phenomenologically, based on spectral features and time series data, since the specific details of the physics of the different explosions remain unrevealed. However, the number of these classes is…

This paper presents a novel method for determining the probability that a supernova candidate belongs to a known supernova type (such as Ia, Ibc, IIL, \emph{etc.}), using its photometric information alone. It is validated with Monte Carlo,…

Control of systematic uncertainties in the use of Type Ia supernovae as standardized distance indicators can be achieved through contrasting subsets of observationally-characterized, like supernovae. Essentially, like supernovae at…

Unsupervised 3D object detection methods have emerged to leverage vast amounts of data without requiring manual labels for training. Recent approaches rely on dynamic objects for learning to detect mobile objects but penalize the detections…

Detecting small, densely distributed objects is a significant challenge: small objects often contain less distinctive information compared to larger ones, and finer-grained precision of bounding box boundaries are required. In this paper,…

In this paper, we address the problem of detecting small, dense, and overlapping objects, a major challenge in computer vision. Our focus is on reviewing proposed methods based on deep learning supervised approaches. We provide a detailed…

Detecting object-level changes between two images across possibly different views is a core task in many applications that involve visual inspection or camera surveillance. Existing change-detection approaches suffer from three major…

To alleviate the cost of obtaining accurate bounding boxes for training today's state-of-the-art object detection models, recent weakly supervised detection work has proposed techniques to learn from image-level labels. However, requiring…

Object detection and recognition are important problems in computer vision. Since these problems are meta-heuristic, despite a lot of research, practically usable, intelligent, real-time, and dynamic object detection/recognition methods are…

Despite great progress in object detection, most existing methods work only on a limited set of object categories, due to the tremendous human effort needed for bounding-box annotations of training data. To alleviate the problem, recent…

With large numbers of transients discovered by current and future imaging surveys, machine learning is increasingly applied to light curve and host galaxy properties to select events for follow-up. However, finding rare types of transients…