licongguan/ILM-ASSL
Iterative Loop Method Combining Active and Semi-Supervised Learning for Domain Adaptive Semantic Segmentation
This project helps operations engineers or autonomous vehicle developers improve how their AI systems understand road scenes in new environments. It takes existing labeled road scene data (e.g., from a simulation or one city) and unlabeled images from a new environment, then outputs an improved AI model that accurately identifies objects like roads, cars, and pedestrians in the new, real-world setting. This is crucial for applications like self-driving cars that need to adapt to diverse real-world conditions.
No commits in the last 6 months.
Use this if you need to quickly adapt an existing AI model for road scene analysis to perform accurately in a new, unfamiliar environment with minimal manual labeling effort.
Not ideal if you are starting from scratch with no pre-existing labeled data for a similar domain or if your primary goal is not semantic segmentation of road scenes.
Stars
34
Forks
3
Language
Python
License
—
Category
Last pushed
Mar 28, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/licongguan/ILM-ASSL"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
deepinv/deepinv
DeepInverse: a PyTorch library for solving imaging inverse problems using deep learning
yjxiong/tsn-pytorch
Temporal Segment Networks (TSN) in PyTorch
mhamilton723/STEGO
Unsupervised Semantic Segmentation by Distilling Feature Correspondences
fidler-lab/polyrnn-pp
Inference Code for Polygon-RNN++ (CVPR 2018)
pyxu-org/pyxu
Modular and scalable computational imaging in Python with GPU/out-of-core computing.