Self-supervised Learning
Existing approaches for low-resource text summarization primarily employ large language models (LLMs) like GPT-3 or GPT-4 at inference …
This paper presents EarthView, a comprehensive dataset specifically designed for self-supervision on remote sensing data, intended to …
Sign language is a primary channel for the deaf and hard-hearing to communicate. Sign language consists of many signs with different …
Handling out-of-distribution (OOD) samples has become a major stake in the real-world deploy- ment of machine learning systems. This …
In this paper, we extend the blind-spot based self-supervised denoising by using affinity learning to remove noise from affected …
We explore the downstream task performances for graph neural network (GNN) self-supervised learning (SSL) methods trained on subgraphs …
Applications such as disaster management enormously benefit from rapid availability of satellite observations.
Traditionally, data …
We explore the downstream task performances for graph neural network (GNN) self-supervised learning (SSL) methods trained on subgraphs …
Labeling data is often expensive and time-consuming, especially for tasks such as object detection and instance segmentation, which …
Remote sensing and automatic earth monitoring are key to solve global-scale challenges such as disaster prevention, land use …