6 papers
Reviving ConvNeXt for Efficient Convolutional Diffusion Models
Taesung Kwon, Lorenzo Bianchi, Lennart Wittke +5
Recent diffusion models increasingly favor Transformer backbones, motivated by the remarkable scalability of fully attentional architectures. Yet the locality bias, parameter effic…
One Patch to Caption Them All: A Unified Zero-Shot Captioning Framework
Lorenzo Bianchi, Giacomo Pacini, Fabio Carrara +3
Zero-shot captioners are recently proposed models that utilize common-space vision-language representations to caption images without relying on paired image-text data. To caption…
CountingDINO: A Training-free Pipeline for Class-Agnostic Counting using Unsupervised Backbones
Giacomo Pacini, Lorenzo Bianchi, Luca Ciampi +3
Class-agnostic counting (CAC) aims to estimate the number of objects in images without being restricted to predefined categories. However, while current exemplar-based CAC methods…
Talking to DINO: Bridging Self-Supervised Vision Backbones with Language for Open-Vocabulary Segmentation
Luca Barsellotti, Lorenzo Bianchi, Nicola Messina +5
Open-Vocabulary Segmentation (OVS) aims at segmenting images from free-form textual concepts without predefined training classes. While existing vision-language models such as CLIP…
Is CLIP the main roadblock for fine-grained open-world perception?
Lorenzo Bianchi, Fabio Carrara, Nicola Messina +1
Modern applications increasingly demand flexible computer vision models that adapt to novel concepts not encountered during training. This necessity is pivotal in emerging domains…
The devil is in the fine-grained details: Evaluating open-vocabulary object detectors for fine-grained understanding
Lorenzo Bianchi, Fabio Carrara, Nicola Messina +2
Recent advancements in large vision-language models enabled visual object detection in open-vocabulary scenarios, where object classes are defined in free-text formats during infer…