Preserving Fine-Grained Droplet Structures by Spatial Gaussian Blurring Against Pooling Deformation in U-Net-Based Semantic Segmentation

Pooling operations in convolutional neural networks often lead to the loss of fine-grained object features, particularly when those objects occupy only a few pixels (e.g., <inline-formula> <tex-math notation="LaTeX">$5 \times 5$ </tex-math></inline-formula> or smaller). This problem is critical in d...

Disgrifiad llawn

Manylion Llyfryddiaeth

Prif Awduron:	Wei Lun Lim, Matthew Y. W. Teow, Richard T. K. Wong, Sian Lun Lau
Fformat:	Artigo
Iaith:	Inglês
Cyhoeddwyd:	IEEE 2026-01-01
Cyfres:	IEEE Access
Pynciau:	Computer vision fine-grained semantic segmentation Gaussian blurring graph convolution convolutional network
Mynediad Ar-lein:	https://ieeexplore.ieee.org/document/11394763/
Tagiau:	Ychwanegu Tag Dim Tagiau, Byddwch y cyntaf i dagio'r cofnod hwn!