TRCGL-Net uses text-guided conditional diffusion for tail-class augmentation, channel reweighting, class-aware attention, and label co-occurrence GCN to raise tail-class mAP to 0.4904 on PadChest.
Bag of tricks for long-tailed multi-label classification on chest x-rays.arXiv preprint arXiv:2308.08853, 2023
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
TRCGL-Net: A Long-Tailed Multi-Label Chest X-Ray Classification Framework with Generative Data Augmentation and Label Co-Occurrence Modeling
TRCGL-Net uses text-guided conditional diffusion for tail-class augmentation, channel reweighting, class-aware attention, and label co-occurrence GCN to raise tail-class mAP to 0.4904 on PadChest.