no code implementations • 17 Apr 2024 • Aayush Dhakal, Subash Khanal, Srikumar Sastry, Adeel Ahmad, Nathan Jacobs
In this work, we present a deep-learning model, GeoBind, that can infer about multiple modalities, specifically text, image, and audio, from satellite imagery of a location.
1 code implementation • 9 Apr 2024 • Srikumar Sastry, Subash Khanal, Aayush Dhakal, Nathan Jacobs
We present GeoSynth, a model for synthesizing satellite images with global style and image-driven layout control.
no code implementations • 13 Dec 2023 • Srikumar Sastry, Xin Xing, Aayush Dhakal, Subash Khanal, Adeel Ahmad, Nathan Jacobs
Further, we propose a novel proximity-aware evaluation metric that enables evaluating species distribution models using any pixel-level representation of ground-truth species range map.
no code implementations • 12 Dec 2023 • Michael Lanier, Aayush Dhakal, Zhexiao Xiong, Arthur Li, Nathan Jacobs, Yevgeniy Vorobeychik
In critical operations where aerial imagery plays an essential role, the integrity and trustworthiness of data are paramount.
1 code implementation • 29 Oct 2023 • Srikumar Sastry, Subash Khanal, Aayush Dhakal, Di Huang, Nathan Jacobs
We propose a metadata-aware self-supervised learning~(SSL)~framework useful for fine-grained classification and ecological mapping of bird species around the world.
1 code implementation • 4 Oct 2023 • Oscar Skean, Aayush Dhakal, Nathan Jacobs, Luis Gonzalo Sanchez Giraldo
However, these two approaches are difficult to combine due to the computational complexity of computing eigenvalues.
1 code implementation • 19 Sep 2023 • Subash Khanal, Srikumar Sastry, Aayush Dhakal, Nathan Jacobs
We focus on the task of soundscape mapping, which involves predicting the most probable sounds that could be perceived at a particular geographic location.
Ranked #1 on Cross-Modal Retrieval on SoundingEarth (using extra training data)
no code implementations • 29 Jul 2023 • Aayush Dhakal, Adeel Ahmad, Subash Khanal, Srikumar Sastry, Hannah Kerner, Nathan Jacobs
For a given location and overhead image, our model predicts the expected CLIP embeddings of the ground-level scenery.