AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

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

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

ICCV 2025 · Vision-language and multimodal › CLIP and zero-shot · approach: Open-vocabulary alignment from VLMs · 35 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace DINOv2 with DINO as visual backbone (ablation)Talk2DINO · Pascal VOC20 (ViT-B)mIoU: 87.1 -> 27.3Hurt
use DINOv2 with registers (ablation)Talk2DINO ViT-B · Pascal VOC20mIoU: 74.2 -> 87.1Improved
use DINOv2 with registers (ablation)Talk2DINO ViT-S · Pascal Context 59mIoU: 38.3 -> 35.3Hurt
use nonlinear tanh mapping instead of linear projection on text (ablation)Talk2DINO · Pascal Context 59 (ViT-B)mIoU: 37.9 -> 39.8Improved
also map the vision side with the learned projection (ablation)Talk2DINO · Pascal Context 59 (ViT-B)mIoU: 39.8 -> 27.3Hurt
select max-similarity attention head instead of standard average (ablation)Talk2DINO · Pascal Context 59 (ViT-B)mIoU: 36.9 -> 39.8Improved
select max-similarity attention head instead of standard average (ablation)Talk2DINO · Pascal VOC20 (ViT-B)mIoU: 89.6 -> 87.1Hurt
add attention-based background cleaning (ablation)Talk2DINO · COCO Object (ViT-B, no refinement)mIoU: 37.1 -> 41.0Improved
add attention-based background cleaning (ablation)Talk2DINO · Pascal VOC21 (ViT-B, no refinement)mIoU: 59.9 -> 61.5Improved
keep CLIP text encoder frozen rather than unfreezing last layer (ablation)Talk2DINO · Pascal Context 59 (ViT-B)mIoU: 31.5 -> 39.8Improved
align CLS text token instead of average of text tokens (ablation)Talk2DINO · Pascal Context 59 (ViT-B)mIoU: 37.9 -> 39.8Improved
use ViT-L instead of ViT-B without mask refinement (ablation)Talk2DINO · 8-benchmark averagemIoU (avg): 43.8 -> 42.8No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy