/CheXFusion

[ ICCV CVAMD 2023] Official implementation of "CheXFusion: Effective Fusion of Multi-View Features using Transformers for Long-Tailed Chest X-Ray Classification" 🏆 1st place solution 🏆 for the ICCV CVAMD 2023 Shared Task: CXR-LT: Multi-Label Long-Tailed Classification on Chest X-Rays.

Primary LanguagePythonMIT LicenseMIT

CheXFusion

This is the official PyTorch Implementation of "CheXFusion: Effective Fusion of Multi-View Features using Transformers for Long-Tailed Chest X-Ray Classification"

Presentation Video

Slides

Poster

🏆 1st place solution 🏆 for the ICCV CVAMD 2023 Shared Task: CXR-LT: Multi-Label Long-Tailed Classification on Chest X-Rays.

Paper published in ICCV proceedings with oral presentation.

Imgur

Update June 7:

A co-authored paper discussing the challenge was published in Medical Image Analysis!

ChexFusion remained 1st place, considerably outperforming other teams, even under various distribution shifts.

Results

ChexFusion showed 1st place results in all metrics. Public Leaderboard

Imgur