knn

A researcher reports a surprising 50-point accuracy gap between frozen SigLIP2 (92%) and DINOv2 (41%) embeddings on a fine-grained car classification task using k-NN, seeking insight on whether a linear probe would close the gap or if DINOv2 is unsuited for retrieval.

Manticore Search introduces early termination for HNSW-based KNN vector search, reducing distance computations by up to 80% for large k values while maintaining precision within 2-4% of full search.

pynear 2.3 is a fast KNN library with SIMD acceleration and drop-in compatibility with scikit-learn, offering exact and approximate cosine indices and outperforming Faiss on binary descriptors in some contexts.