Unlocking VLM Potential on Satellite Imagery Through Fine-Tuning
Mistral AI News6 days agoTutorialMistral AI demonstrates how LoRA fine-tuning adapts Pixtral-12B to satellite imagery, a specialized visual domain where prompting alone is unreliable. Using the Aerial Image Dataset, the post compares a prompt-based baseline against a fine-tuned model across 30 scene classes. Accuracy rose from 0.56 to 0.91, while invalid label hallucinations dropped from 5% to 0.1%.
AI2 發表 OlmoEarth v1.1：更高效的開源地球觀測模型家族★ 70
Hugging Face Blog26 days agoReleaseThe Allen Institute for AI (AI2) has officially released OlmoEarth v1.1 on Hugging Face. This is a brand-new family of open-source foundation models designed…
使用機器學習爭分奪秒救援災民：Hugging Face 探討 AI 在災害應變中的關鍵角色
Hugging Face Blog1,199 days agoCommentaryThis blog post from Hugging Face explores how machine learning (ML) can assist rescue workers in a race against time to save lives during natural disasters…
微調 CLIP 模型以辨識遙測（衛星）影像與文本描述
Hugging Face Blog1,705 days agoTutorialThis blog post from the Hugging Face community provides a detailed walkthrough of how to fine-tune OpenAI's CLIP (Contrastive Language-Image Pre-training)…