Parameter-Efficient 3D Segmentation of Liver and Liver tumors: Depthwise factorization Scales Better Than Dense Convolution with Spatial Dimensionality
cs.CV, cs.LG
Submitted: 2026-09-27
Updated: 2026-09-27
Code: https://github.com/adham-synbio/3D_shift_UNet
Terminology
Sources
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- nnU-Net: Self-adapting Framework for U-Net-Based Medical Image Segmentation
- SGDR: Stochastic Gradient Descent with Warm Restarts
- Decoupled Weight Decay Regularization
- Learning Sparse Neural Networks through $L_0$ Regularization
- Instance Normalization: The Missing Ingredient for Fast Stylization
- S$^2$-MLPv2: Improved Spatial-Shift MLP Architecture for Vision
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models