Lucas Hu - Academia.edu (original) (raw)
Uploads
Papers by Lucas Hu
A hybrid recommender system for suggesting CDN (content delivery network) providers to various we... more A hybrid recommender system for suggesting CDN (content delivery network) providers to various websites
A hybrid recommender system for suggesting CDN (content delivery network) providers to various we... more A hybrid recommender system for suggesting CDN (content delivery network) providers to various websites
ArXiv, 2020
Recent work has shown that deep learning models can be used to classify land-use data from geospa... more Recent work has shown that deep learning models can be used to classify land-use data from geospatial satellite imagery. We show that when these deep learning models are trained on data from specific continents/seasons, there is a high degree of variability in model performance on out-of-sample continents/seasons. This suggests that just because a model accurately predicts land-use classes in one continent or season does not mean that the model will accurately predict land-use classes in a different continent or season. We then use clustering techniques on satellite imagery from different continents to visualize the differences in landscapes that make geospatial generalization particularly difficult, and summarize our takeaways for future satellite imagery-related applications.
IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium
We propose an iterative clustering-based label super-resolution approach and epitome-based approa... more We propose an iterative clustering-based label super-resolution approach and epitome-based approach to weakly supervised semantic segmentation, as well as a deep learning-based postprocessing step for land cover segmentation. An ensemble of the iterative clustering and epitome approaches with the proposed postprocessing step results in a top validation leaderboard average accuracy of 70.43%. A similar ensemble, that also considers class accuracy feedback from the leaderboard, achieves a top Track 1 leaderboard average accuracy of 57.49%.
Representation learning for link prediction within social networks
A hybrid recommender system for suggesting CDN (content delivery network) providers to various we... more A hybrid recommender system for suggesting CDN (content delivery network) providers to various websites
A hybrid recommender system for suggesting CDN (content delivery network) providers to various we... more A hybrid recommender system for suggesting CDN (content delivery network) providers to various websites
ArXiv, 2020
Recent work has shown that deep learning models can be used to classify land-use data from geospa... more Recent work has shown that deep learning models can be used to classify land-use data from geospatial satellite imagery. We show that when these deep learning models are trained on data from specific continents/seasons, there is a high degree of variability in model performance on out-of-sample continents/seasons. This suggests that just because a model accurately predicts land-use classes in one continent or season does not mean that the model will accurately predict land-use classes in a different continent or season. We then use clustering techniques on satellite imagery from different continents to visualize the differences in landscapes that make geospatial generalization particularly difficult, and summarize our takeaways for future satellite imagery-related applications.
IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium
We propose an iterative clustering-based label super-resolution approach and epitome-based approa... more We propose an iterative clustering-based label super-resolution approach and epitome-based approach to weakly supervised semantic segmentation, as well as a deep learning-based postprocessing step for land cover segmentation. An ensemble of the iterative clustering and epitome approaches with the proposed postprocessing step results in a top validation leaderboard average accuracy of 70.43%. A similar ensemble, that also considers class accuracy feedback from the leaderboard, achieves a top Track 1 leaderboard average accuracy of 57.49%.
Representation learning for link prediction within social networks