A Parameter-Efficient Fine-Tuning (PEFT) LoRA adapter trained on the lunar-pits-dataset for the DINOv3 vision foundation model. It enables specialized feature extraction for lunar surface analysis while keeping the base model frozen. The model provides Matryoshka embeddings and supports visual evaluation techniques such as t-SNE and saliency maps.
Lunar Dinov3 Lora is an Other AI project. It focuses on adapting DINOv3 for specialized computer vision tasks on lunar imagery with minimal parameters. Lunar Dinov3 Lora is an open-source project aimed at developers. The project is open source (Open Source). It runs on the web, the command line, and API.
It is developed by F1nnSBK, and it first shipped in 2024. Key capabilities include loRA adapter, feature extraction, and visual embeddings.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Same category — not a similarity match