A deep learning model for per-pixel, multi-label detection of building changes in bi-temporal satellite and aerial imagery. MBCTD classifies each pixel independently into three change categories, allowing overlapping labels (e.g., a replacement site marked as both demolished and new simultaneously).
Related
di37/animated-machine-learning-algorithm: Watch scikit-learn models learn and predict: live training and inference animations, narrated lessons and Manim videos for California Housing (regression) and Titanic (classification)
Watch scikit-learn models learn and predict: live training and inference animations, narrated lessons and Manim videos for California Housing (regression) and Titanic (classificati...
phasyn/phasyn-studio: AI filmmaking on your own GPUs: a self-hosted studio that generates short videos with sound and still images.
AI filmmaking on your own GPUs: a self-hosted studio that generates short videos with sound and still images.
sybil-solutions/inference-optimisation-skill: Agent skill for hill-climbing local LLM serving speed (decode, speculative decoding, prefill, KV, startup, TTFT) on any hardware and quantization
Agent skill for hill-climbing local LLM serving speed (decode, speculative decoding, prefill, KV, startup, TTFT) on any hardware and quantization