{"slug": "learning-woody-clearing-with-loss-alignment-for-zero-shot-regrowth-and-woody", "title": "Learning Woody Clearing With Loss Alignment for Zero-Shot Regrowth and Woody Segmentation", "summary": "Researchers introduced a loss scaling coefficient α to align deep learning models for woody clearing detection with end-user Fβ metrics, increasing precision by 1.85x or recall by 1.12x on 7 years of Sentinel-2 imagery from New South Wales, Australia. Their augmentation and generation techniques enabled zero-shot transfer to regrowth and woody segmentation, reducing segmentation error by up to 18.2% and achieving an F1 score of 0.845 for zero-shot regrowth detection.", "body_md": "arXiv:2608.26489v1 Announce Type: new\nAbstract: Detecting woody clearing is vital for managing biodiversity. Deep learning models can detect change in woody vegetation from bitemporal remote sensing imagery, however generated products may not meet end-user specifications due to unaligned loss definitions. Further limitations of deep learning models are the reliance on large datasets which can be difficult to attain for spatially rare and ambiguous events such as regrowth detection. In this work we train a model to detect woody change using bitemporal Sentinel-2 imagery consisting of 7 years' worth of annual imagery across the state of New South Wales, Australia. To align the objective of the model with end-user metrics, we introduce the loss scaling coefficient $\\alpha$ which transforms the objective to optimize for specific $F_{\\beta}$ scores. Introducing $\\alpha$ was found to increase precision by 1.85x or recall by 1.12x. We propose input imagery augmentation and generation techniques that allow the woody change detection model to zero-shot transfer to regrowth and woody segmentation tasks. For woody segmentation, image generation techniques using activation maximization with low $\\alpha$ values for stability and image generation techniques derived from handcrafted features utilizing a mosaic of clearing patches and artificial trees for contextual grounding were found to outperform prior woody segmentation works of the study area, reducing the overall error by up to 18.2%. For zero-shot woody regrowth, creating pseudo-post and prior images resulted in the model achieving an F1 score of 0.845, creating a foundation for future regrowth detection work.", "url": "https://wpnews.pro/news/learning-woody-clearing-with-loss-alignment-for-zero-shot-regrowth-and-woody", "canonical_source": "https://arxiv.org/abs/2608.26489", "published_at": "2026-08-28 04:00:00+00:00", "updated_at": "2026-08-28 04:22:08.781146+00:00", "lang": "en", "topics": ["machine-learning", "computer-vision"], "entities": ["arXiv", "Sentinel-2", "New South Wales"], "alternates": {"html": "https://wpnews.pro/news/learning-woody-clearing-with-loss-alignment-for-zero-shot-regrowth-and-woody", "markdown": "https://wpnews.pro/news/learning-woody-clearing-with-loss-alignment-for-zero-shot-regrowth-and-woody.md", "text": "https://wpnews.pro/news/learning-woody-clearing-with-loss-alignment-for-zero-shot-regrowth-and-woody.txt", "jsonld": "https://wpnews.pro/news/learning-woody-clearing-with-loss-alignment-for-zero-shot-regrowth-and-woody.jsonld"}}