Papers › Deep ViT Features as Dense Visual Descriptors

Deep ViT Features as Dense Visual Descriptors

10 Dec 2021arXiv:2112.05814archive 2025-07-28

Shir Amir, Yossi Gandelsman, Shai Bagon, Tali Dekel

We study the use of deep features extracted from a pretrained Vision Transformer (ViT) as dense visual descriptors. We observe and empirically demonstrate that such features, when extractedfrom a self-supervised ViT model (DINO-ViT), exhibit several striking properties, including: (i) the features encode powerful, well-localized semantic information, at high spatial granularity, such as object parts; (ii) the encoded semantic information is shared across related, yet different object categories, and (iii) positional bias changes gradually throughout the layers. These properties allow us to design simple methods for a variety of applications, including co-segmentation, part co-segmentation and semantic correspondences. To distill the power of ViT features from convoluted design choices, we restrict ourselves to lightweight zero-shot methodologies (e.g., binning and clustering) applied directly to the features. Since our methods require no additional training nor data, they are readily applicable across a variety of domains. We show by extensive qualitative and quantitative evaluation that our simple methodologies achieve competitive results with recent state-of-the-art supervised methods, and outperform previous unsupervised methods by a large margin. Code is available in dino-vit-features.github.io.

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="2112.05814")

Code

Syntology Ran 1 of 6 code samples harvested from 1 repository linked to this paper; 5 have no recorded run. Of those that ran: 1 ran · violated contract.

By repository: community (archive-listed): 6 samples from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

shiramir/dino-vit-features mentioned on GitHubpytorchMIT 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

6 samples harvested; 1 ran; 0 honoured the contract we drafted; 5 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.

1ran · violated contract
5unverified

Licence: 0 of the 6 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 shiramir/dino-vit-features. “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.

str2bool shiramir/dino-vit-features/extractor.py community (archive-listed) ran · violated contract MIT (permissive) · 7c508037b40522af · report
chunk_cosine_sim shiramir/dino-vit-features/correspondences.py community (archive-listed) unverified MIT (permissive) · 3f4bf3c8828c54f5 · report
draw_correspondences shiramir/dino-vit-features/correspondences.py community (archive-listed) unverified MIT (permissive) · 63bcd56229e4d4bf · report
draw_cosegmentation shiramir/dino-vit-features/cosegmentation.py community (archive-listed) unverified MIT (permissive) · 29b1f22fa41c2726 · report
draw_cosegmentation_binary_masks shiramir/dino-vit-features/cosegmentation.py community (archive-listed) unverified MIT (permissive) · a7b722998654c756 · report
draw_part_cosegmentation shiramir/dino-vit-features/part_cosegmentation.py community (archive-listed) unverified MIT (permissive) · ffd5efd075d81f39 · report

Tasks

Feature UpsamplingSemantic correspondence

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformerVision 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