Related papers: Contrast data mining for the MSSM from strings

There has been great interest recently in applying nonparametric kernel mixtures in a hierarchical manner to model multiple related data samples jointly. In such settings several data features are commonly present: (i) the related samples…

Image-language matching tasks have recently attracted a lot of attention in the computer vision field. These tasks include image-sentence matching, i.e., given an image query, retrieving relevant sentences and vice versa, and region-phrase…

This work proposes a multi-image matching method to estimate semantic correspondences across multiple images. In contrast to the previous methods that optimize all pairwise correspondences, the proposed method identifies and matches only a…

Real-world data often follow a long-tailed distribution with a high imbalance in the number of samples between classes. The problem with training from imbalanced data is that some background features, common to all classes, can be…

Learning-based multi-view stereo (MVS) methods have made impressive progress and surpassed traditional methods in recent years. However, their accuracy and completeness are still struggling. In this paper, we propose a new method to enhance…

One of the goals of the landscape program in string theory is to extract information about the space of string vacua in the form of statistical correlations between phenomenological features that are otherwise uncorrelated in field theory.…

Scaling methods have long been utilized to simplify and cluster high-dimensional data. However, the general latent spaces across all predefined groups derived from these methods sometimes do not fall into researchers' interest regarding…

Semantic segmentation models struggle to generalize in the presence of domain shift. In this paper, we introduce contrastive learning for feature alignment in cross-domain adaptation. We assemble both in-domain contrastive pairs and…

Accurately predicting the likelihood of interaction between two objects (compound-protein sequence, user-item, author-paper, etc.) is a fundamental problem in Computer Science. Current deep-learning models rely on learning accurate…

Short text classification has gained significant attention in the information age due to its prevalence and real-world applications. Recent advancements in graph learning combined with contrastive learning have shown promising results in…

Learning semantically meaningful sentence embeddings is an open problem in natural language processing. In this work, we propose a sentence embedding learning approach that exploits both visual and textual information via a multimodal…

Hierarchical classification is a crucial task in many applications, where objects are organized into multiple levels of categories. However, conventional classification approaches often neglect inherent inter-class relationships at…

Mining human-brain networks to discover patterns that can be used to discriminate between healthy individuals and patients affected by some neurological disorder, is a fundamental task in neuroscience. Learning simple and interpretable…

Contrastive learning has been the dominant approach to train state-of-the-art sentence embeddings. Previous studies have typically learned sentence embeddings either through the use of human-annotated natural language inference (NLI) data…

Accurate mapping of forests is critical for forest management and carbon stocks monitoring. Deep learning is becoming more popular in Earth Observation (EO), however, the availability of reference data limits its potential in wide-area…

Graph-level contrastive learning, aiming to learn the representations for each graph by contrasting two augmented graphs, has attracted considerable attention. Previous studies usually simply assume that a graph and its augmented graph as a…

Recent developments in string theory have reinforced the notion that the space of stable supersymmetric and non-supersymmetric string vacua fills out a ``landscape'' whose features are largely unknown. It is then hoped that progress in…

Using Large Language Models (LLMs) in an evolutionary or other iterative search framework have demonstrated significant potential in automated algorithm design. However, the underlying fitness landscape, which is critical for understanding…

The landscape of low-energy effective field theories stemming from string theory is too vast for a systematic exploration. However, the meadows of the string landscape may be fertile ground for the application of machine learning…

Contrastive learning has demonstrated great success in representation learning, especially for image classification tasks. However, there is still a shortage in studies targeting regression tasks, and more specifically applications on…