Lorenzo Bianchi

vision-language model (2) self-supervised learning (2) benchmark evaluation (1) vision transformer (1) density estimation (1) object detection (1) visual grounding (1) unsupervised feature extraction (1) vision language model (1) open-vocabulary segmentation (1) fine-grained understanding (1) density map estimation (1) class-agnostic counting (1) open-vocabulary object detection (1) object prototype (1) dynamic vocabulary (1) training-free pipeline (1) self-supervised visual model (1) feature alignment (1) semantic localization (1)