Transformers for recognition in overhead imagery: A reality check

F Luzi, A Gupta, L Collins… - Proceedings of the …, 2023 - openaccess.thecvf.com
There is evidence that transformers offer state-of-the-art recognition performance on tasks
involving overhead imagery (eg, satellite imagery). However, it is difficult to make unbiased …

Weed detection in UAV images of cereal crops with instance segmentation

A Gromova - 2021 - diva-portal.org
Modern weeding is predominantly carried out by spraying whole fields with toxic pesticides,
a process that accomplishes the main goal of eliminating weeds, but at a cost of the local …

Occlusion-Ordered Semantic Instance Segmentation

S Baselizadeh - 2023 - uwspace.uwaterloo.ca
Conventional semantic 'instance'segmentation methods offer a segmentation mask for each
object instance in an image along with its semantic class label. These methods excel in …

Targeting LAG-3+ T cells for cancer immunotherapy

L Capitani - 2024 - orca.cardiff.ac.uk
Lymphocyte activation gene 3 (LAG-3) is a promising co-inhibitory receptor target which has
been shown to negatively regulate T cell responses. However, the minutiae of LAG-3 …

BoundNet: Pixel Level Boundary Marking and Tracking of Instance Video Objects

M Jayasree, KA Sunitha, A Brindha… - 2022 3rd …, 2022 - ieeexplore.ieee.org
Object segmentation is the inevitable result of object recognition and semantic segmentation
when moving from coarse to fine inference. Despite many efforts in segmenting instances …

Identification of alkaline fens using convolutional neural networks and multispectral satellite imagery

J Jernberg - 2021 - diva-portal.org
The alkaline fen is a particularly valuable type of wetland with unique characteristics. Due to
anthropogenic risk factors and the sensitive nature of the fens, protection is highly prioritized …