Related papers: Multi-Label Guided Soft Contrastive Learning for E…

Robust radio signal recognition is fundamental to spectrum management, electromagnetic space security, and intelligent wireless applications, yet existing deep-learning methods rely heavily on large labeled datasets and struggle to capture…

Automated animal censuses with aerial imagery are a vital ingredient towards wildlife conservation. Recent models are generally based on deep learning and thus require vast amounts of training data. Due to their scarcity and minuscule size,…

Recent advances in self-supervised learning (SSL) have largely closed the gap with supervised ImageNet pretraining. Despite their success these methods have been primarily applied to unlabeled ImageNet images, and show marginal gains when…

Modern Earth observation (EO) increasingly leverages deep learning to harness the scale and diversity of satellite imagery across sensors and regions. While recent foundation models have demonstrated promising generalization across EO…

In this paper, we introduce a novel method designed to enhance label efficiency in satellite imagery analysis by integrating semi-supervised learning (SSL) with active learning strategies. Our approach utilizes contrastive learning together…

Foundation models are transforming Earth Observation (EO), yet the diversity of EO sensors and modalities makes a single universal model unrealistic. Multiple specialized EO foundation models (EOFMs) will likely coexist, making efficient…

Vision foundation models have attracted significant attention for their ability to leverage large-scale unlabeled visual data. This advantage is particularly important in remote sensing, where data acquisition is costly and annotation often…

Self-supervised contrastive learning offers a means of learning informative features from a pool of unlabeled data. In this paper, we delve into another useful approach -- providing a way of selecting a core-set that is entirely unlabeled.…

Direct Low Earth Orbit satellite-to-handheld links are expected to be part of a new era in satellite communications. Space-Division Multiple Access precoding is a technique that reduces interference among satellite beams, therefore…

Contrastive representation learning has proven to be an effective self-supervised learning method. Most successful approaches are based on Noise Contrastive Estimation (NCE) and use different views of an instance as positives that should be…

Self-supervised Contrastive Learning (CL) has been recently shown to be very effective in preventing deep networks from overfitting noisy labels. Despite its empirical success, the theoretical understanding of the effect of contrastive…

Convolutional networks have marked their place over the last few years as the best performing model for various visual tasks. They are, however, most suited for supervised learning from large amounts of labeled data. Previous attempts have…

Multi-modal data in Earth Observation (EO) presents a huge opportunity for improving transfer learning capabilities when pre-training deep learning models. Unlike prior work that often overlooks multi-modal EO data, recent methods have…

Self-supervised learning has proven to be an effective way to learn representations in domains where annotated labels are scarce, such as medical imaging. A widely adopted framework for this purpose is contrastive learning and it has been…

Advances in Earth observation (EO) foundation models have unlocked the potential of big satellite data to learn generic representations from space, benefiting a wide range of downstream applications crucial to our planet. However, most…

Self-supervised learning (SSL) has emerged as a powerful approach to learning representations, particularly in the field of computer vision. However, its application to dependent data, such as temporal and spatio-temporal domains, remains…

Soft labels in image classification are vector representations of an image's true classification. In this paper, we investigate soft labels in the context of satellite object detection. We propose using detections as the basis for a new…

Contrastive learning methods enforce label distance relationships in feature space to improve representation capability for regression models. However, these methods highly depend on label information to correctly recover ordinal…

Contrastive learning has moved the state of the art for many tasks in computer vision and information retrieval in recent years. This poster is the first work that applies supervised contrastive learning to the task of product matching in…

Contrastive learning has proven to be highly efficient and adaptable in shaping representation spaces across diverse modalities by pulling similar samples together and pushing dissimilar ones apart. However, two key limitations persist: (1)…