nv-tlabs/GSCNN
Gated-Shape CNN for Semantic Segmentation (ICCV 2019)
Introduces gated shape modules that explicitly model object boundaries alongside semantic predictions, improving segmentation accuracy at class edges. Built on PyTorch with WiderResNet38 backbone, the architecture combines spatial feature learning with boundary-aware gating to refine per-pixel classifications. Includes pretrained weights for Cityscapes and supports multi-GPU training across NVIDIA hardware.
937 stars. No commits in the last 6 months.
Stars
937
Forks
200
Language
Python
License
—
Category
Last pushed
Oct 23, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/nv-tlabs/GSCNN"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
hkchengrex/CascadePSP
[CVPR 2020] CascadePSP: Toward Class-Agnostic and Very High-Resolution Segmentation via Global...
jiwoon-ahn/irn
Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relations, CVPR 2019 (Oral)
lim-anggun/FgSegNet
FgSegNet: Foreground Segmentation Network, Foreground Segmentation Using Convolutional Neural...
suyukun666/UFO
Official PyTorch implementation of the “A Unified Transformer Framework for Co-Segmentation,...
Chrisding/seal
Code for Simultaneous Edge Alignment and Learning (SEAL)