Výsledky vyhledávání

Dissertation/ Thesis

Achieving More with Less: Learning Generalizable Neural Networks With Less Labeled Data and Computational Overheads

Autor: Bu, Jie

Recent advancements in deep learning have demonstrated its incredible ability to learn generalizable patterns and relationships automatically from data in a number of mainstream applications. However, the generalization power of deep learning methods

Externí odkaz: http://hdl.handle.net/10919/114108

Zobrazit plný text záznamu

Report

Beyond Discriminative Regions: Saliency Maps as Alternatives to CAMs for Weakly Supervised Semantic Segmentation

Autor: Maruf, M., Daw, Arka, Dutta, Amartya, Bu, Jie, Karpatne, Anuj

In recent years, several Weakly Supervised Semantic Segmentation (WS3) methods have been proposed that use class activation maps (CAMs) generated by a classifier to produce pseudo-ground truths for training segmentation models. While CAMs are good at

Externí odkaz: http://arxiv.org/abs/2308.11052

Zobrazit plný text záznamu

Report

Let There Be Order: Rethinking Ordering in Autoregressive Graph Generation

Autor: Bu, Jie, Mehrab, Kazi Sajeed, Karpatne, Anuj

Conditional graph generation tasks involve training a model to generate a graph given a set of input conditions. Many previous studies employ autoregressive models to incrementally generate graph components such as nodes and edges. However, as graphs

Externí odkaz: http://arxiv.org/abs/2305.15562

Zobrazit plný text záznamu

Report

Mitigating Propagation Failures in Physics-informed Neural Networks using Retain-Resample-Release (R3) Sampling

Autor: Daw, Arka, Bu, Jie, Wang, Sifan, Perdikaris, Paris, Karpatne, Anuj

Despite the success of physics-informed neural networks (PINNs) in approximating partial differential equations (PDEs), PINNs can sometimes fail to converge to the correct solution in problems involving complicated PDEs. This is reflected in several

Externí odkaz: http://arxiv.org/abs/2207.02338

Zobrazit plný text záznamu