Mixing real UAV imagery with 2101 AI-generated image-mask pairs improves semantic segmentation F1 scores for fine-grained forest species by over 15 percentage points overall and up to 30 points for rare classes.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2representative citing papers
Argues that XAI techniques should be routine in ecological computer vision validation to confirm models rely on biologically meaningful cues rather than spurious correlations.
citing papers explorer
-
Leveraging Image Generators to Address Training Data Scarcity: The Gen4Regen Dataset for Forest Regeneration Mapping
Mixing real UAV imagery with 2101 AI-generated image-mask pairs improves semantic segmentation F1 scores for fine-grained forest species by over 15 percentage points overall and up to 30 points for rare classes.
-
Explainable AI for Biodiversity Monitoring and Ecological Image Analysis
Argues that XAI techniques should be routine in ecological computer vision validation to confirm models rely on biologically meaningful cues rather than spurious correlations.