Codes related to DCASE2021 Task 1 - Acoustic Scene Classification
-
Updated
Aug 12, 2021 - Python
#
squeeze-excitation
Here are 4 public repositories matching this topic...
Implementation of a compact Attention Half U-Net with Attention Gates and Squeeze-and-Excitation blocks for medical image segmentation. Features a modular PyTorch pipeline, BCE-Dice hybrid loss, mixed-precision training, cosine annealing scheduler, and reproducible evaluation tools.
computer-vision deep-learning pytorch medical-image-segmentation unet-pytorch dice-loss attention-gate binary-segmentation squeeze-excitation
-
Updated
Jun 11, 2026 - Python
Hybrid underwater image enhancement using blind CNN denoising and perceptual LAB colour loss — trained and evaluated on the UIEB benchmark dataset.
computer-vision deep-learning cnn pytorch resnet image-restoration blind-denoising squeeze-excitation underwater-image-enhancement perceptual-loss-lab-color-space
-
Updated
Apr 6, 2026 - Jupyter Notebook
"Ablation study on CNN depth, data augmentation, and background removal for efficient plant disease classification — 97.8% accuracy on potato, <7.5M params, <55ms inference."
attention-mechanism plantvillage precision-agriculture background-removal edge-deployment lightweight-cnn ablation-study model-efficiency squeeze-excitation
-
Updated
Jun 25, 2026 - Python
Improve this page
Add a description, image, and links to the squeeze-excitation topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the squeeze-excitation topic, visit your repo's landing page and select "manage topics."