Talking to DINO: Bridging Self-Supervised Vision Backbones with Language for Open-Vocabulary Segmentation (ICCV 2025)

Luca Barsellotti*  Lorenzo Bianchi*  Nicola Messina  Fabio Carrara  Marcella Cornia  Lorenzo Baraldi  Fabrizio Falchi  Rita Cucchiara

Project Page | Paper | Code

About

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 can generate segmentation masks by leveraging coarse spatial information from Vision Transformers, they face challenges in spatial localization due to their global alignment of image and text features. Conversely, self-supervised visual models like DINO excel in fine-grained visual encoding but lack integration with language. To bridge this gap, we present Talk2DINO, a novel hybrid approach that combines the spatial accuracy of DINOv2 with the language understanding of CLIP. Our approach aligns the textual embeddings of CLIP to the patch-level features of DINOv2 through a learned mapping function without the need to fine-tune the underlying backbones. At training time, we exploit the attention maps of DINOv2 to selectively align local visual patches with textual embeddings. We show that the powerful semantic and localization abilities of Talk2DINO can enhance the segmentation process, resulting in more natural and less noisy segmentations, and that our approach can also effectively distinguish foreground objects from the background. Experimental results demonstrate that Talk2DINO achieves state-of-the-art performance across several unsupervised OVS benchmarks.

Sample Usage

Mapping CLIP Text Embeddings to DINOv2 space with Talk2DINO

We can use Talk2DINO to map CLIP text embeddings into the DINOv2 patch embedding space.

from transformers import AutoModel
from torchvision.io import read_image

# Device setup
device = 'cuda' if torch.cuda.is_available() else 'cpu'

# Model Loading
model = AutoModel.from_pretrained("lorebianchi98/Talk2DINO-ViTL").to(device).eval()

# Embedding generation
with torch.no_grad():
    text_embed = model.encode_text("a pikachu")
    image_embed = model.encode_image(image)

# normalize the features to perform cosine similarity
text_embed = text_embed / text_embed.norm(dim=-1, keepdim=True)
image_embed = image_embed / image_embed.norm(dim=-1, keepdim=True)

similarity = (image_embed @ text_embed.T).squeeze(0, -1).cpu().numpy()

Demo

In demo.ipynb we provide a simple example on how to use Talk2DINO for inference on a given image with custom textual categories. Result:

Installation

To use the Hugging Face interface for inference:

# Clone the repository
git clone https://huggingface.co/lorebianchi98/Talk2DINO-ViTL
cd Talk2DINO-ViTL

# Install dependencies
pip install -r requirements.txt

# Install PyTorch and torchvision with the appropriate CUDA version
pip install torch torchvision --index-url https://download.pytorch.org/whl/cu126

For the full MMCV interface to perform evaluation on segmentation benchmarks, please refer to the original Talk2DINO repository.

Qualitative Results

Reference

If you found this code useful, please cite the following paper:

@misc{barsellotti2024talkingdinobridgingselfsupervised,
      title={Talking to DINO: Bridging Self-Supervised Vision Backbones with Language for Open-Vocabulary Segmentation}, 
      author={Luca Barsellotti and Lorenzo Bianchi and Nicola Messina and Fabio Carrara and Marcella Cornia and Lorenzo Baraldi and Fabrizio Falchi and Rita Cucchiara},
      year={2024},
      eprint={2411.19331},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2411.19331}, 
}