Uncertainty-guided diffusion inpainting augments semantic segmentation data by regenerating context around hard regions and training only on preserved original pixels, yielding mIoU gains on rare classes in Cityscapes, UAVID, and BDD100K.
Class-balanced loss based on effective number of samples
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CV 3verdicts
UNVERDICTED 3representative citing papers
SemLT3D introduces semantic-guided expert distillation with a language MoE module and CLIP projection to enrich features for long-tailed classes in camera-only 3D detection.
TaxoNet uses a dual-margin objective to reshape decision boundaries in long-tailed fine-grained plant taxonomy, improving rare-class geometry under open-world conditions.
citing papers explorer
-
Preserve the Hard, Regenerate the Rest: Uncertainty-Guided Synthetic Training Data Augmentation with Diffusion Models
Uncertainty-guided diffusion inpainting augments semantic segmentation data by regenerating context around hard regions and training only on preserved original pixels, yielding mIoU gains on rare classes in Cityscapes, UAVID, and BDD100K.
-
SemLT3D: Semantic-Guided Expert Distillation for Camera-only Long-Tailed 3D Object Detection
SemLT3D introduces semantic-guided expert distillation with a language MoE module and CLIP projection to enrich features for long-tailed classes in camera-only 3D detection.
-
Dual-Margin Embedding for Fine-Grained Long-Tailed Plant Taxonomy
TaxoNet uses a dual-margin objective to reshape decision boundaries in long-tailed fine-grained plant taxonomy, improving rare-class geometry under open-world conditions.