AmirMansurian/AICSD

Adaptive Inter-Class Similarity Distillation for Semantic Segmentation (MTAP 2025)

37
/ 100
Emerging

This project helps computer vision engineers develop more efficient image segmentation models. It takes a larger, high-performing segmentation model and a smaller, less complex model as input. The output is a smaller model that achieves significantly improved segmentation accuracy, making it more suitable for deployment in resource-constrained environments. Computer vision practitioners focused on deploying models for image analysis would benefit from this.

Use this if you need to deploy an image segmentation model to devices with limited computational power, such as mobile phones or embedded systems, without sacrificing too much accuracy.

Not ideal if your primary goal is to achieve the absolute highest segmentation accuracy regardless of model size or computational efficiency.

image-segmentation model-optimization computer-vision edge-ai deep-learning-deployment
No License No Package No Dependents
Maintenance 6 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 16 / 25

How are scores calculated?

Stars

29

Forks

7

Language

Python

License

Last pushed

Nov 14, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/AmirMansurian/AICSD"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.