4 citations · 6 across the 4 of their papers we have counts for
4 papers
Are Deep Learning Models Robust to Partial Object Occlusion in Visual Recognition Tasks?
Kaleb Kassaw, Francesco Luzi, Leslie M. Collins +1
Image classification models, including convolutional neural networks (CNNs), perform well on a variety of classification tasks but struggle under conditions of partial occlusion, i…
Segment anything, from space?
Simiao Ren, Francesco Luzi, Saad Lahrichi +4
Recently, the first foundation model developed specifically for image segmentation tasks was developed, termed the "Segment Anything Model" (SAM). SAM can segment objects in input…
Meta-Learning for Color-to-Infrared Cross-Modal Style Transfer
Evelyn A. Stump, Francesco Luzi, Leslie M. Collins +1
Recent object detection models for infrared (IR) imagery are based upon deep neural networks (DNNs) and require large amounts of labeled training imagery. However, publicly availab…
Transformers For Recognition In Overhead Imagery: A Reality Check
Francesco Luzi, Aneesh Gupta, Leslie Collins +2
There is evidence that transformers offer state-of-the-art recognition performance on tasks involving overhead imagery (e.g., satellite imagery). However, it is difficult to make u…