Related papers: CLAP. I. Resolving miscalibration for deep learnin…
Improving distance measurements in large imaging surveys is a major challenge to better reveal the distribution of galaxies on a large scale and to link galaxy properties with their environments. Photometric redshifts can be efficiently…
Wide-field optical imaging surveys are efficient at identifying galaxy clusters, but optically identified clusters suffer from projection effects--physically unassociated galaxies along the line of sight can be misidentified as cluster…
Contrastive language-audio pretraining~(CLAP) has been developed to align the representations of audio and language, achieving remarkable performance in retrieval and classification tasks. However, current CLAP struggles to capture temporal…
In many classification problems it is desirable to output well-calibrated probabilities on the different classes. We propose a robust, non-parametric method of calibrating probabilities called SplineCalib that utilizes smoothing splines to…
We present improved methods for using stars found in astronomical exposures to calibrate both star and galaxy colors as well as to adjust the instrument flat field. By developing a spectroscopic model for the SDSS stellar locus in…
Open-vocabulary audio language models (ALMs), like Contrastive Language Audio Pretraining (CLAP), represent a promising new paradigm for audio-text retrieval using natural language queries. In this paper, for the first time, we perform…
Contrastive Language-Image Pretraining (CLIP) achieves strong generalization in vision-language tasks by aligning images and texts in a shared embedding space. However, recent findings show that CLIP-like models still underutilize…
We develop a novel method to explore the galaxy-halo connection using the galaxy imaging surveys by modeling the projected two-point correlation function measured from the galaxies with reasonable photometric redshift measurements. By…
Computer-aided diagnosis plays a salient role in more accessible and accurate cardiopulmonary diseases classification and localization on chest radiography. Millions of people get affected and die due to these diseases without an accurate…
We investigate the expected cosmological constraints from a combination of weak lensing and large-scale galaxy clustering using realistic redshift distributions. Introducing a systematic bias in the weak lensing redshift distributions (of…
Measuring biodiversity is crucial for understanding ecosystem health. While prior works have developed machine learning models for taxonomic classification of photographic images and DNA separately, in this work, we introduce a multimodal…
Complementary-Label Learning (CLL) is a weakly-supervised learning problem that aims to learn a multi-class classifier from only complementary labels, which indicate a class to which an instance does not belong. Existing approaches mainly…
Discrepancies between cosmological parameter estimates from cosmic shear surveys and from recent Planck cosmic microwave background measurements challenge the ability of the highly successful $\Lambda$CDM model to describe the nature of the…
Change detection (CD) is an important yet challenging task in the Earth observation field for monitoring Earth surface dynamics. The advent of deep learning techniques has recently propelled automatic CD into a technological revolution.…
Mixup~\cite{zhang2017mixup} is a recently proposed method for training deep neural networks where additional samples are generated during training by convexly combining random pairs of images and their associated labels. While simple to…
We develop a general method to "self-calibrate" observations of galaxy clustering with respect to systematics associated with photometric calibration errors. We first point out the danger posed by the multiplicative effect of calibration…
In unsupervised adaptation for vision-language models such as CLIP, pseudo-labels derived from zero-shot predictions often exhibit significant noise, particularly under domain shifts or in visually complex scenarios. Conventional…
We present a comprehensive experimental study on pretrained feature extractors for visual out-of-distribution (OOD) detection, focusing on adapting contrastive language-image pretrained (CLIP) models. Without fine-tuning on the training…
Image-text contrastive models like CLIP have wide applications in zero-shot classification, image-text retrieval, and transfer learning. However, they often struggle on compositional visio-linguistic tasks (e.g., attribute-binding or…
We consider the application of relative self-calibration using overlap regions to spectroscopic galaxy surveys that use slit-less spectroscopy. This method is based on that developed for the SDSS by Padmanabhan at al. (2008) in that we…