We propose an encoder-decoder for open-vocabulary semantic segmentation comprising a hierarchical encoder-based cost map generation and a gradual fusion decoder. We introduce a category early ...

Abstract: Change detection is a critical task in earth observation applications. Recently, deep-learning-based methods have shown promising performance and are quickly adopted in change detection.

Marble is a modular, configuration-driven suite for training, evaluating, and performing inference on state-of-the-art pretrained music models. It leverages LightningCLI to provide easy extensibility ...

Abstract: Accurate time series forecasting is critical in a variety of fields, including transportation, weather prediction, energy management, infrastructure monitoring, and finance. Forecasting ...