Methods › Computer Vision › Image Models › DPT
Dense Prediction Transformer
DPT
Introduced by René Ranftl et al. in Vision Transformers for Dense Prediction
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Dense Prediction Transformers (DPT) are a type of vision transformer for dense prediction tasks.
The input image is transformed into tokens (orange) either by extracting non-overlapping patches followed by a linear projection of their flattened representation (DPT-Base and DPT-Large) or by applying a ResNet-50 feature extractor (DPT-Hybrid). The image embedding is augmented with a positional embedding and a patch-independent readout token (red) is added. The tokens are passed through multiple transformer stages. The tokens are reassembled from different stages into an image-like representation at multiple resolutions (green). Fusion modules (purple) progressively fuse and upsample the representations to generate a fine-grained prediction.
In Syntology about another paper, arXiv:2205.11166: repository known, no verified implementation (declared_code; repositories: 2 listed of 2 in the graph, strongest link: official). About another paper: this answer is about arXiv:2205.11166, while the archive credits arXiv:2103.13413.
From the lookup's note on this name: The same name also belongs to the paper “DPT: Deformable Patch-based Transformer for Visual Recognition” (arXiv:2107.14467, 138 citations), which the lookup finds cited far more than the paper this answer is about (39 citations), so this answer may be about a different sense of the name. For arXiv:2107.14467: its page on this site · ask the lookup about it.
Origin paper of this answer, arXiv:2205.11166 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 7 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified (of 12 harvested samples). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.
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: 25 · with a code link: 10 · where Syntology ran a sample: 5 (4 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (5 of 25 tagged: 4 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 25 of 25, 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.
-
Can In-Context Reinforcement Learning Recover From Reward Poisoning Attacks? 7 Jun 2025 · 0 repositories · arXiv:2506.06891
-
Filtering Learning Histories Enhances In-Context Reinforcement Learning 21 May 2025 · 0 repositories · arXiv:2505.15143
-
SAR Object Detection with Self-Supervised Pretraining and Curriculum-Aware Sampling 17 Apr 2025 · 0 repositories · arXiv:2504.13310
-
Random Policy Enables In-Context Reinforcement Learning within Trust Horizons 25 Oct 2024 · 0 repositories · arXiv:2410.19982
-
Theoretical limits of descending ℓ₀ sparse-regression ML algorithms 10 Oct 2024 · 0 repositories · arXiv:2410.07651
-
Endogenous Crashes as Phase Transitions 12 Aug 2024 · 0 repositories · arXiv:2408.06433
-
Pretraining Decision Transformers with Reward Prediction for In-Context Multi-task Structured Bandit Learning 7 Jun 2024 · 0 repositories · arXiv:2406.05064
-
Developmental Pretraining (DPT) for Image Classification Networks 1 Dec 2023 · 1 repository · arXiv:2312.00304
-
Enhancing Diffusion Models with 3D Perspective Geometry Constraints 1 Dec 2023 · 0 repositories · arXiv:2312.00944
-
Depth-guided Free-space Segmentation for a Mobile Robot 3 Nov 2023 · 0 repositories · arXiv:2311.01966
-
The serotonergic psychedelic N,N-dipropyltryptamine alters information-processing dynamics in cortical neural circuits 31 Oct 2023 · 0 repositories · arXiv:2310.20582
-
Supervised Pretraining Can Learn In-Context Reinforcement Learning 26 Jun 2023 · 0 repositories · arXiv:2306.14892
-
High-Resolution Synthetic RGB-D Datasets for Monocular Depth Estimation 2 May 2023 · 0 repositories · arXiv:2305.01732
-
Diffusion Models and Semi-Supervised Learners Benefit Mutually with Few Labels 21 Feb 2023 · 3 repositories · arXiv:2302.10586Syntology official (archive's flag): 18 ran · 18 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 10 where Syntology's instrument failed) · 4 unverified (of 22 harvested samples) · 9 pointer-only (licence)
-
Denoising and Prompt-Tuning for Multi-Behavior Recommendation 12 Feb 2023 · 1 repository · arXiv:2302.05862
-
DPTDR: Deep Prompt Tuning for Dense Passage Retrieval 24 Aug 2022 · 2 repositories · arXiv:2208.11503
-
Dual Modality Prompt Tuning for Vision-Language Pre-Trained Model 17 Aug 2022 · 1 repository · arXiv:2208.08340
-
SSDPT: Self-Supervised Dual-Path Transformer for Anomalous Sound Detection in Machine Condition Monitoring 6 Aug 2022 · 0 repositories · arXiv:2208.03421
-
Prompt Tuning for Discriminative Pre-trained Language Models 23 May 2022 · 1 repository · arXiv:2205.11166Syntology official (archive's flag): 7 ran · 7 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified (of 12 harvested samples)
-
Declaration-based Prompt Tuning for Visual Question Answering 5 May 2022 · 1 repository · arXiv:2205.02456
-
Integration of neural network and fuzzy logic decision making compared with bilayered neural network in the simulation of daily dew point temperature 23 Feb 2022 · 0 repositories · arXiv:2202.12256
-
Towards 3D Scene Reconstruction from Locally Scale-Aligned Monocular Video Depth 3 Feb 2022 · 0 repositories · arXiv:2202.01470
-
Detail-Preserving Transformer for Light Field Image Super-Resolution 2 Jan 2022 · 1 repository · arXiv:2201.00346Syntology official (archive's flag): 10 ran · 10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 11 unverified (of 21 harvested samples) · 21 pointer-only (licence)
-
DPT: Deformable Patch-based Transformer for Visual Recognition 30 Jul 2021 · 1 repository · arXiv:2107.14467Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)
-
Vision Transformers for Dense Prediction 24 Mar 2021 · 15 repositories · arXiv:2103.13413Syntology 65 ran (of which 19 constructed an object rather than computing a result; 32 with no instrument failure: 0 honoured, 0 violated, 32 with no contract checked; 33 where Syntology's instrument failed) · 51 unverified (of 116 harvested samples) · 15 pointer-only (licence)
Tasks archive 2025-07-28
20 shown of 53 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
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
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