Early-exit deep neural network-a comprehensive survey

H Rahmath P, V Srivastava, K Chaurasia… - ACM Computing …, 2024 - dl.acm.org
Deep neural networks (DNNs) typically have a single exit point that makes predictions by
running the entire stack of neural layers. Since not all inputs require the same amount of …

HyperGCN–a multi-layer multi-exit graph neural network to enhance hyperspectral image classification

H Rahmath P, K Chaurasia, A Gupta… - International Journal of …, 2024 - Taylor & Francis
Graph neural networks (GNNs) have recently garnered significant attention due to their
exceptional performance across various applications, including hyperspectral (HS) image …

Adaptive early-exit inference in graph neural networks based hyperspectral image classification

P Haseena Rahmath, K Chaurasia - International Conference on …, 2023 - Springer
Hyperspectral image (HSI) classification is a prominent and active research topic in the field
of remote sensing. The unique capabilities of hyperspectral imaging, which captures …

Adaptive Early-Exit Inference in Graph Neural Networks Based Hyperspectral

PH Rahmath, K Chaurasia - Intelligent Systems Design and …, 2024 - books.google.com
Hyperspectral image (HSI) classification is a prominent and active research topic in the field
of remote sensing. The unique capabili-ties of hyperspectral imaging, which captures …