Search Results for author:
Found 10 papers, 5 papers with code
Optimizing Data Distribution and Kernel Performance for Efficient Training of Chemistry Foundation Models: A Case Study with MACE
For the training phase, we identify symmetric tensor contraction as the key computational kernel in MACE and optimize this kernel to improve the overall performance.
Relative Distance Guided Dynamic Partition Learning for Scale-Invariant UAV-View Geo-Localization
Specifically, we propose a distance guided dynamic partition learning strategy~(DGDPL), consisting of a square partition strategy and a distance-guided adjustment strategy.
The Impact of Scanner Domain Shift on Deep Learning Performance in Medical Imaging: an Experimental Study
This phenomenon, scanner domain shift, can result in a drop in the performance of deep neural networks which are trained on data acquired by one scanner and tested on another.
SDPL: Shifting-Dense Partition Learning for UAV-View Geo-Localization
We propose a dense partition strategy (DPS), dividing the image into multiple parts to explore contextual information while explicitly maintaining the global structure.
Towards Natural Language-Guided Drones: GeoText-1652 Benchmark with Spatial Relation Matching
Navigating drones through natural language commands remains challenging due to the dearth of accessible multi-modal datasets and the stringent precision requirements for aligning visual and textual data.
Deep learning radiomics for assessment of gastroesophageal varices in people with compensated advanced chronic liver disease
Validation analysis revealed that the AUCs of DLRP were 0. 91 for GEV (95% CI 0. 90 to 0. 93, p < 0. 05) and 0. 88 for HRV (95% CI 0. 86 to 0. 89, p < 0. 01), which were significantly and robustly better than canonical risk indicators, including the value of LSM and SSM.
Learning Cross-view Geo-localization Embeddings via Dynamic Weighted Decorrelation Regularization
Cross-view geo-localization aims to spot images of the same location shot from two platforms, e. g., the drone platform and the satellite platform.
Multiple-environment Self-adaptive Network for Aerial-view Geo-localization
This task is mostly regarded as an image retrieval problem.
Each Part Matters: Local Patterns Facilitate Cross-view Geo-localization
Existing methods usually concentrate on mining the fine-grained feature of the geographic target in the image center, but underestimate the contextual information in neighbor areas.
Ranked #3 on
Drone navigation
on University-1652
Inexact Krylov iterations and relaxation strategies with fast-multipole boundary element method
We take advantage of a unique property of Krylov iterations that allow lower accuracy of the matrix-vector products as convergence proceeds, and propose a relaxation strategy based on progressively decreasing $p$.
Numerical Analysis Computational Physics 35Q35, 35Q99, 45B05, 76D07, 76Z99
