73 citations · 121 across the 14 of their papers we have counts for
15 papers
Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learning
Colorado J. Reed, Ritwik Gupta, Shufan Li +7
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 wi…
Prior Knowledge-Guided Attention in Self-Supervised Vision Transformers
Kevin Miao, Akash Gokul, Raghav Singh +5
Recent trends in self-supervised representation learning have focused on removing inductive biases from training pipelines. However, inductive biases can be useful in settings when…
Snowpack Estimation in Key Mountainous Water Basins from Openly-Available, Multimodal Data Sources
Malachy Moran, Kayla Woputz, Derrick Hee +7
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…
Refine and Represent: Region-to-Object Representation Learning
Akash Gokul, Konstantinos Kallidromitis, Shufan Li +4
Recent works in self-supervised learning have demonstrated strong performance on scene-level dense prediction tasks by pretraining with object-centric or region-based correspondenc…
SunCast: Solar Irradiance Nowcasting from Geosynchronous Satellite Data
Dhileeban Kumaresan, Richard Wang, Ernesto Martinez +4
When cloud layers cover photovoltaic (PV) panels, the amount of power the panels produce fluctuates rapidly. Therefore, to maintain enough energy on a power grid to match demand, u…
HyperionSolarNet: Solar Panel Detection from Aerial Images
Poonam Parhar, Ryan Sawasaki, Alberto Todeschini +4
With the effects of global climate change impacting the world, collective efforts are needed to reduce greenhouse gas emissions. The energy sector is the single largest contributor…
Multi-source Few-shot Domain Adaptation
Xiangyu Yue, Zangwei Zheng, Colorado Reed +3
Multi-source Domain Adaptation (MDA) aims to transfer predictive models from multiple, fully-labeled source domains to an unlabeled target domain. However, in many applications, re…
Self-supervised Contrastive Learning for Irrigation Detection in Satellite Imagery
Chitra Agastya, Sirak Ghebremusse, Ian Anderson +3
Climate change has caused reductions in river runoffs and aquifer recharge resulting in an increasingly unsustainable crop water demand from reduced freshwater availability. Achiev…
Invariant Information Bottleneck for Domain Generalization
Bo Li, Yifei Shen, Yezhen Wang +6
Invariant risk minimization (IRM) has recently emerged as a promising alternative for domain generalization. Nevertheless, the loss function is difficult to optimize for nonlinear…
DETReg: Unsupervised Pretraining with Region Priors for Object Detection
Amir Bar, Xin Wang, Vadim Kantorov +6
Recent self-supervised pretraining methods for object detection largely focus on pretraining the backbone of the object detector, neglecting key parts of detection architecture. In…
Self-Supervised Pretraining Improves Self-Supervised Pretraining
Colorado J. Reed, Xiangyu Yue, Ani Nrusimha +9
While self-supervised pretraining has proven beneficial for many computer vision tasks, it requires expensive and lengthy computation, large amounts of data, and is sensitive to da…
Region Similarity Representation Learning
Tete Xiao, Colorado J Reed, Xiaolong Wang +2
We present Region Similarity Representation Learning (ReSim), a new approach to self-supervised representation learning for localization-based tasks such as object detection and se…
SelfAugment: Automatic Augmentation Policies for Self-Supervised Learning
Colorado J Reed, Sean Metzger, Aravind Srinivas +2
A common practice in unsupervised representation learning is to use labeled data to evaluate the quality of the learned representations. This supervised evaluation is then used to…
Multi-source Domain Adaptation in the Deep Learning Era: A Systematic Survey
Sicheng Zhao, Bo Li, Colorado Reed +2
In many practical applications, it is often difficult and expensive to obtain enough large-scale labeled data to train deep neural networks to their full capability. Therefore, tra…
Scaling the Indian Buffet Process via Submodular Maximization
Colorado Reed, Zoubin Ghahramani
Inference for latent feature models is inherently difficult as the inference space grows exponentially with the size of the input data and number of latent features. In this work,…