Methods › Computer Vision › Vision Transformers › DINO

self-DIstillation with NO labels

DINO

208 papers tagged archive 2025-07-28

Introduced by Mathilde Caron et al. in Emerging Properties in Self-Supervised Vision Transformers

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

DINO (self-distillation with no labels) is a self-supervised learning method that directly predicts the output of a teacher network - built with a momentum encoder - using a standard cross-entropy loss.

In the example to the right, DINO is illustrated in the case of one single pair of views (x₁, x₂) for simplicity. The model passes two different random transformations of an input image to the student and teacher networks. Both networks have the same architecture but other parameters. The output of the teacher network is centered with a mean computed over the batch. Each network outputs a K dimensional feature normalized with a temperature softmax over the feature dimension. Their similarity is then measured with a cross-entropy loss. A stop-gradient (sg) operator is applied to the teacher to propagate gradients only through the student. The teacher parameters are updated with the student parameters' exponential moving average (ema).

PaperSourceSee Code · facebookresearch/dino

In Syntology name not resolved (unknown_name). Other entries in Syntology's graph carry this name; the lookup's note below says what that means for this name.

From the lookup's note on this name: Nothing resolved to this name, but 3 entries in Syntology's graph carry it; the most cited is the paper “DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection” (arXiv:2203.03605, 3,083 citations). The lookup reads this as a miss of its own name matching, not a gap in coverage: the graph holds the name under a spelling the lookup did not reach. For arXiv:2203.03605: its page on this site · ask the lookup about it.

Near matches the lookup lists, each a different name: CQ-DINO; DINO-AD; DINO-vMF; DINO-QPM; Shape-DINO; DINO-AugSeg; DINO-Tracker; DINO Teacher.

Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.

Papers archive 2025-07-28

archive papers tagged: 208 · with a code link: 105 · where Syntology ran a sample: 30 (27 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (30 of 208 tagged: 27 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument)

Page 1 of 3: papers 1 to 100 of 208, newest first by the archive's date (ties by slug), in archive order.

Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.

Tasks archive 2025-07-28

20 shown of 225 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Semantic Segmentation44
Object Detection38
object-detection33
Segmentation29
Self-Supervised Learning28
Object25
Contrastive Learning13
Representation Learning13
Image Classification11
Instance Segmentation11
Image Generation10
image-classification9
Clustering8
Data Augmentation7
Scene Understanding7
Transfer Learning7
Image Segmentation6
Retrieval6
Unsupervised Semantic Segmentation6
Anomaly Detection5

Usage over time archive 2025-07-28

Papers per year tagged with DINO: 2021 to 2025, peak 108 108 0 2021: 1 paper 2021 2022: 5 papers 2022 2023: 44 papers 2023 2024: 108 papers 2024 2025: 50 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (208 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Vision TransformersSelf-Supervised Learning

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