Dimensionality compression and expansion in deep neural networks

S Recanatesi, M Farrell, M Advani, T Moore… - arxiv preprint arxiv …, 2019 - arxiv.org
Datasets such as images, text, or movies are embedded in high-dimensional spaces.
However, in important cases such as images of objects, the statistical structure in the data …

Exploring Learned Representations of Neural Networks with Principal Component Analysis

A Harlev, A Engel, P Stinis, T Chiang - arxiv preprint arxiv:2309.15328, 2023 - arxiv.org
Understanding feature representation for deep neural networks (DNNs) remains an open
question within the general field of explainable AI. We use principal component analysis …

Semi-self-supervised segmentation of oranges with small sample sizes

K Volle, P Ganesh, TF Burks… - 2020 ASABE Annual …, 2020 - elibrary.asabe.org
Visually detecting and masking fruit can be regarded as a vital first step in autonomous
harvesting. Given the constrained domain, general purpose segmentation networks are …