Related papers: An Algorithm for the Visualization of Relevant Pat…

Visual Recognition is one of the fundamental challenges in AI, where the goal is to understand the semantics of visual data. Employing mid-level representation, in particular, shifted the paradigm in visual recognition. The mid-level…

The ability to automatically and robustly self-verify periodicity present in time-series astronomical data is becoming more important as data sets rapidly increase in size. The age of large astronomical surveys has rendered manual…

We propose a technique for making Convolutional Neural Network (CNN)-based models more transparent by visualizing input regions that are 'important' for predictions -- or visual explanations. Our approach, called Gradient-weighted Class…

Modern astronomical surveys produce millions of light curves of variable sources. These massive data sets challenge the community to create automatic light-curve processing methods for detection, classification, and characterisation of…

Astronomy has entered the multi-messenger data era and Machine Learning has found widespread use in a large variety of applications. The exploitation of synoptic (multi-band and multi-epoch) surveys, like LSST (Legacy Survey of Space and…

Visual localization, i.e., the problem of camera pose estimation, is a central component of applications such as autonomous robots and augmented reality systems. A dominant approach in the literature, shown to scale to large scenes and to…

We propose a technique to train semantic part-based models of object classes from Google Images. Our models encompass the appearance of parts and their spatial arrangement on the object, specific to each viewpoint. We learn these rich…

Galactic rotation curves are crucial for understanding the distribution of mass in galaxies. Despite advances in precision observations, there are discrepancies between the inferred mass from luminosity and the observed rotational…

Over the last decade, Convolutional Neural Network (CNN) models have been highly successful in solving complex vision problems. However, these deep models are perceived as "black box" methods considering the lack of understanding of their…

Many astrophysical phenomena are time-varying, in the sense that their intensity, energy spectrum, and/or the spatial distribution of the emission suddenly change. This paper develops a method for modeling a time series of images. Under the…

In this work, we aim to reconstruct a time-varying 3D model, capable of rendering photo-realistic renderings with independent control of viewpoint, illumination, and time, from Internet photos of large-scale landmarks. The core challenges…

Explainability is a longstanding challenge in deep learning, especially in high-stakes domains like healthcare. Common explainability methods highlight image regions that drive an AI model's decision. Humans, however, heavily rely on…

We address the key question of how object part representations can be found from the internal states of CNNs that are trained for high-level tasks, such as object classification. This work provides a new unsupervised method to learn…

Fine-grained visual recognition is to classify objects with visually similar appearances into subcategories, which has made great progress with the development of deep CNNs. However, handling subtle differences between different…

Interpretability and small labelled datasets are key issues in the practical application of deep learning, particularly in areas such as medicine. In this paper, we present a semi-supervised technique that addresses both these issues by…

Patch-level image representation is very important for object classification and detection, since it is robust to spatial transformation, scale variation, and cluttered background. Many existing methods usually require fine-grained…

Catalogs of periodic variable stars contain large numbers of periodic light-curves (photometric time series data from the astrophysics domain). Separating anomalous objects from well-known classes is an important step towards the discovery…

Recently, Vision-Language Pre-training (VLP) techniques have greatly benefited various vision-language tasks by jointly learning visual and textual representations, which intuitively helps in Optical Character Recognition (OCR) tasks due to…

The development of synoptic sky surveys has led to a massive amount of data for which resources needed for analysis are beyond human capabilities. To process this information and to extract all possible knowledge, machine learning…

Large Vision Language Models (VLMs), such as CLIP, have significantly contributed to various computer vision tasks, including object recognition and object detection. Their open vocabulary feature enhances their value. However, their…