megvii-research/ML-GCN
A PyTorch implementation of ML-GCN for multi-label image recognition using graph convolutional networks.

Velocity · 7d
+0.5
★ / day
Trend
→steady
star history
This repository provides a PyTorch implementation of the CVPR 2019 paper Multi-Label Image Recognition with Graph Convolutional Networks. The method uses a GCN to model label co-occurrence dependencies for improved multi-label image classification. It includes pre-trained checkpoints for COCO and VOC datasets and demo scripts for evaluation.