Papers › Talking to DINO: Bridging Self-Supervised Vision Backbones with Language for...

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

28 Nov 2024arXiv:2411.19331archive 2025-07-28

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

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. Source code and models are publicly available at: https://lorebianchi98.github.io/Talk2DINO/.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2411.19331")

Code

Syntology Ran 0 of 10 code samples harvested from 1 repository linked to this paper; 10 have no recorded run.

By repository: official repository: 10 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

lorebianchi98/Talk2DINO officialmentioned on GitHubpytorchApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

10 samples harvested; 0 ran; 0 honoured the contract we drafted; 10 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

10unverified

Licence: 0 of the 10 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from lorebianchi98/Talk2DINO. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

average_text_tokens lorebianchi98/Talk2DINO/src/hooks.py official repository unverified Apache-2.0 (permissive) · 0856dea1909e47d8 · report
const_lr lorebianchi98/Talk2DINO/src/train_util.py official repository unverified Apache-2.0 (permissive) · 04508bbd793cdfb9 · report
cosine_lr lorebianchi98/Talk2DINO/src/train_util.py official repository unverified Apache-2.0 (permissive) · 932d44bbf8bd0e3f · report
generate_caption lorebianchi98/Talk2DINO/dino_extraction_v2.py official repository unverified Apache-2.0 (permissive) · e56697ee94f100ea · report
get_image_and_text_tensor lorebianchi98/Talk2DINO/src/metrics.py official repository unverified Apache-2.0 (permissive) · 18f13c09e4fe6f6c · report
i2t lorebianchi98/Talk2DINO/src/metrics.py official repository unverified Apache-2.0 (permissive) · 5dbf1b65ee3ef568 · report
process_self_attention lorebianchi98/Talk2DINO/src/hooks.py official repository unverified Apache-2.0 (permissive) · b5ac7bbd59fafe04 · report
t2i lorebianchi98/Talk2DINO/src/metrics.py official repository unverified Apache-2.0 (permissive) · 314ef23cfc918b24 · report
train lorebianchi98/Talk2DINO/src/train_util.py official repository unverified Apache-2.0 (permissive) · 5b444cb020759a17 · report
warn_and_continue lorebianchi98/Talk2DINO/src/open_vocabulary_segmentation/datasets/builder.py official repository unverified Apache-2.0 (permissive) · cc5ea4ff3586026b · report

Tasks

Segmentation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

ALIGNAttentionCLIPDINODense ConnectionsLayer NormalizationLinear LayerMulti-Head AttentionResidual ConnectionSoftmaxVision Transformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections