Shypd.aiThe largest open index of AI toolsAViD is an open-source framework that enables fine-tuning of vision-language grounding models on custom datasets. It extends Grounding DINO with parameter-efficient adaptation, LoRA support, and EMA stabilization.
Trending
About
AViD is a streamlined toolkit designed for fine-tuning state-of-the-art vision-language detection models with parameter-efficient adaptation. Built upon the powerful Grounding DINO framework, AViD introduces capabilities for fine-tuning image-to-text grounding on custom datasets, which is crucial for applications requiring precise alignment between textual descriptions and image regions. Key features include a complete fine-tuning pipeline, parameter-efficient training with LoRA (allowing training of only ~2% of parameters), and EMA stabilization to retain pre-trained knowledge. It also offers optional phrase-based NMS for removing redundant boxes and includes a sample fashion dataset for immediate experimentation. The framework provides a comprehensive evaluation suite with metrics like mAP, Precision, Recall, and F1 Score, along with visualizations and detailed reporting.
Capabilities
Pricing & Plans
Open Source
Free
FAQs
Trending
