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 View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 10 code samples harvested from 1 repository linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 1 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 10 samples from 1 repository, 9 ran (9 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-25 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

lorebianchi98/Talk2DINO officialmentioned on GitHubpytorchApache-2.0Syntology: 10 samples, 9 ran (0 instrument-failed) · 1 unverified 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: 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 1 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · violated contract
8ran
1unverified

Licence: 2 of the 10 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. 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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 1 sample that ran, the graph records a signature this page does not show: an argument's recorded type or element kind is a printout of an object in Syntology's harness (such as a mock object, a class or a pandas printout), not the type of an input, so it does not describe the call's shape. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

lorebianchi98/Talk2DINO official repository 10 samples, 9 ran (0 instrument-failed) · 1 unverified
average_text_tokens src/hooks.py ran Apache-2.0 (permissive) · 0856dea1909e47d8 · report fixture: signature text_embeddings:Tensor/3/float, mask:Tensor/2/bool, keep_cls:bool/0/bool, keep_end_seq:bool/0/bool · returned Tensor · level recorded 2026-09-25
const_lr src/train_util.py ran Apache-2.0 (permissive) here; the stored copy is pointer only · 04508bbd793cdfb9 · report fixture: signature optimizer:SGD/0/?, base_lr:float/0/float, warmup_length:int/0/int, steps:int/0/int · returned function · level recorded 2026-09-25
cosine_lr in 31 papers src/train_util.py ran Apache-2.0 (permissive) here; the stored copy is pointer only · 932d44bbf8bd0e3f · report fixture: signature optimizer:SGD/0/?, base_lr:float/0/float, warmup_length:int/0/int, steps:int/0/int · returned function · level recorded 2026-09-26
get_image_and_text_tensor src/metrics.py ran Apache-2.0 (permissive) · 18f13c09e4fe6f6c · report fixture: signature path:str/0/str, feature_name:str/0/str, text_features:str/0/str, model:NoneType/0/?, return_capts_and_imms:bool/0/bool · returned tuple · level recorded 2026-09-25
i2t src/metrics.py ran Apache-2.0 (permissive) · 5dbf1b65ee3ef568 · report fixture: signature images:ndarray/2/float, captions:ndarray/2/float, npts:int/0/int, return_ranks:bool/0/bool, model:callable/0/? · returned tuple · level recorded 2026-09-25
process_self_attention src/hooks.py ran Apache-2.0 (permissive) · b5ac7bbd59fafe04 · report fixture: signature output:Tensor/3/float, batch_size:int/0/int, num_tokens:int/0/int, num_attn_heads:int/0/int, embed_dim:int/0/int, scale:float/0/float, num_global_tokens:int/0/int, ret_self_attn_maps:bool/0/bool · returned Tensor · level recorded 2026-09-25
t2i src/metrics.py ran Apache-2.0 (permissive) · 314ef23cfc918b24 · report fixture: signature images:ndarray/2/float, captions:ndarray/2/float, npts:int/0/int, return_ranks:bool/0/bool, model:callable/0/? · returned tuple · level recorded 2026-09-25
train in 522 papers src/train_util.py ran Apache-2.0 (permissive) · 5b444cb020759a17 · report fixture: returned float · level recorded 2026-09-25
warn_and_continue src/open_vocabulary_segmentation/datasets/builder.py ran · violated contract Apache-2.0 (permissive) · cc5ea4ff3586026b · report fixture: signature exn:ValueError/0/? · returned bool · level recorded 2026-09-25
generate_caption in 21 papers dino_extraction_v2.py unverified Apache-2.0 (permissive) · e56697ee94f100ea · 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