Related papers: Astromer 2

Earth observation (EO) foundation models have emerged as an effective approach to derive latent representations of the Earth system from various remote sensing sensors. These models produce embeddings that can be used as analysis-ready…

We propose an efficient lighting estimation pipeline that is suitable to run on modern mobile devices, with comparable resource complexities to state-of-the-art mobile deep learning models. Our pipeline, PointAR, takes a single RGB-D image…

In real-world scenarios, although data entities may possess inherent relationships, the specific graph illustrating their connections might not be directly accessible. Latent graph inference addresses this issue by enabling Graph Neural…

With the growing amount of astronomical data, there is an increasing need for automated data processing pipelines, which can extract scientific information from observation data without human interventions. A critical aspect of these…

One of the primary areas of interest in High Performance Computing is the improvement of performance of parallel workloads. Nowadays, compilable source code-based optimization tasks that employ deep learning often exploit LLVM Intermediate…

The ability to learn new concepts continually is necessary in this ever-changing world. However, deep neural networks suffer from catastrophic forgetting when learning new categories. Many works have been proposed to alleviate this…

This paper focuses on improving the effectiveness of the standard 2-layer MLP projection head featured in the SimCLR framework through the use of pretrained autoencoder embeddings. Given a contrastive learning task with a largely unlabeled…

Machine learning has been widely applied to clearly defined problems of astronomy and astrophysics. However, deep learning and its conceptual differences to classical machine learning have been largely overlooked in these fields. The broad…

With the consolidation of deep learning in drug discovery, several novel algorithms for learning molecular representations have been proposed. Despite the interest of the community in developing new methods for learning molecular embeddings…

Live-cell imaging of multiple subcellular structures is essential for understanding subcellular dynamics. However, the conventional multi-color sequential fluorescence microscopy suffers from significant imaging delays and limited number of…

Formal mathematics libraries are rapidly expanding, creating a growing need to refactor verified proofs for maintainability and to improve training data quality for neural provers. However, scalable proof optimization is hindered by…

Many data representations are vectors of continuous values. In particular, deep learning embeddings are data-driven representations, typically either unconstrained in Euclidean space, or constrained to a hypersphere. These may also be…

Lung adenocarcinoma (LUAD) grading depends on accurately identifying growth patterns, which are indicators of prognosis and can influence treatment decisions. Common deep learning approaches to determine the predominant pattern rely on…

Despite recent breakthroughs in deep learning methods for image lighting enhancement, they are inferior when applied to portraits because 3D facial information is ignored in their models. To address this, we present a novel deep learning…

Unsupervised discovery of latent representations, in addition to being useful for density modeling, visualisation and exploratory data analysis, is also increasingly important for learning features relevant to discriminative tasks.…

The benefit of pretrained autoencoders for reinforcement learning in comparison to training on raw observations is already known [1]. In this paper, we address the generation of a compact and information-rich state representation. In…

Building on recent advances in representation learning for wireless channels, this work investigates the cost-benefit trade-offs of high-dimensional channel embeddings in practical systems. We benchmark multiple wireless representations:…

Illumination estimation is the essential step of computational color constancy, one of the core parts of various image processing pipelines of modern digital cameras. Having an accurate and reliable illumination estimation is important for…

Probes are small networks that predict properties of underlying data from embeddings, and they provide a targeted, effective way to illuminate the information contained in embeddings. While analysis through the use of probes has become…

Image editing techniques have rapidly advanced, facilitating both innovative use cases and malicious manipulation of digital images. Deep learning-based methods have recently achieved high accuracy in pixel-level forgery localization, yet…