Search Results for author:
Found 13 papers, 6 papers with code
xT: Nested Tokenization for Larger Context in Large Images
Modern computer vision pipelines handle large images in one of two sub-optimal ways: down-sampling or cropping.
See, Say, and Segment: Teaching LMMs to Overcome False Premises
Current open-source Large Multimodal Models (LMMs) excel at tasks such as open-vocabulary language grounding and segmentation but can suffer under false premises when queries imply the existence of something that is not actually present in the image.
ClimSim: A large multi-scale dataset for hybrid physics-ML climate emulation
The dataset is global in coverage, spans multiple years at high sampling frequency, and is designed such that resulting emulators are compatible with downstream coupling into operational climate simulators.
Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learning
Large, pretrained models are commonly finetuned with imagery that is heavily augmented to mimic different conditions and scales, with the resulting models used for various tasks with imagery from a range of spatial scales.
SatlasPretrain: A Large-Scale Dataset for Remote Sensing Image Understanding
Remote sensing images are useful for a wide variety of planet monitoring applications, from tracking deforestation to tackling illegal fishing.
Snowpack Estimation in Key Mountainous Water Basins from Openly-Available, Multimodal Data Sources
Accurately estimating the snowpack in key mountainous basins is critical for water resource managers to make decisions that impact local and global economies, wildlife, and public policy.
xView3-SAR: Detecting Dark Fishing Activity Using Synthetic Aperture Radar Imagery
Unsustainable fishing practices worldwide pose a major threat to marine resources and ecosystems.
Ranked #1 on
Holdout Set
on xView3-SAR
WiSoSuper: Benchmarking Super-Resolution Methods on Wind and Solar Data
We provide a thorough and extensible benchmark of leading deep learning-based super-resolution techniques, including the enhanced super-resolution generative adversarial network (ESRGAN) and an enhanced deep super-resolution (EDSR) network, on wind and solar data.
Region-level Active Detector Learning
Active learning for object detection is conventionally achieved by applying techniques developed for classification in a way that aggregates individual detections into image-level selection criteria.
Proceedings of NeurIPS 2020 Workshop on Artificial Intelligence for Humanitarian Assistance and Disaster Response
These are the "proceedings" of the 2nd AI + HADR workshop which was held virtually on December 12, 2020 as part of the Neural Information Processing Systems conference.
Proceedings of NeurIPS 2019 Workshop on Artificial Intelligence for Humanitarian Assistance and Disaster Response
These are the "proceedings" of the 1st AI + HADR workshop which was held in Vancouver, Canada on December 13, 2019 as part of the Neural Information Processing Systems conference.
xBD: A Dataset for Assessing Building Damage from Satellite Imagery
xBD is the largest building damage assessment dataset to date, containing 850, 736 building annotations across 45, 362 km\textsuperscript{2} of imagery.
Ranked #5 on
2D Semantic Segmentation
on xBD
Focusing on the Big Picture: Insights into a Systems Approach to Deep Learning for Satellite Imagery
Deep learning tasks are often complicated and require a variety of components working together efficiently to perform well.
