Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

DPT

Dense Prediction Transformer

Computer VisionIntroduced 200025 papers

Description

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.

Papers Using This Method

Can In-Context Reinforcement Learning Recover From Reward Poisoning Attacks?2025-06-07 Filtering Learning Histories Enhances In-Context Reinforcement Learning2025-05-21 SAR Object Detection with Self-Supervised Pretraining and Curriculum-Aware Sampling2025-04-17 Random Policy Enables In-Context Reinforcement Learning within Trust Horizons2024-10-25 Theoretical limits of descending $\ell_0$ sparse-regression ML algorithms2024-10-10 Endogenous Crashes as Phase Transitions2024-08-12 Pretraining Decision Transformers with Reward Prediction for In-Context Multi-task Structured Bandit Learning2024-06-07 Developmental Pretraining (DPT) for Image Classification Networks2023-12-01 Enhancing Diffusion Models with 3D Perspective Geometry Constraints2023-12-01 Depth-guided Free-space Segmentation for a Mobile Robot2023-11-03 The serotonergic psychedelic N,N-dipropyltryptamine alters information-processing dynamics in cortical neural circuits2023-10-31 Supervised Pretraining Can Learn In-Context Reinforcement Learning2023-06-26 High-Resolution Synthetic RGB-D Datasets for Monocular Depth Estimation2023-05-02 Diffusion Models and Semi-Supervised Learners Benefit Mutually with Few Labels2023-02-21 Denoising and Prompt-Tuning for Multi-Behavior Recommendation2023-02-12 DPTDR: Deep Prompt Tuning for Dense Passage Retrieval2022-08-24 Dual Modality Prompt Tuning for Vision-Language Pre-Trained Model2022-08-17 SSDPT: Self-Supervised Dual-Path Transformer for Anomalous Sound Detection in Machine Condition Monitoring2022-08-06 Prompt Tuning for Discriminative Pre-trained Language Models2022-05-23 Declaration-based Prompt Tuning for Visual Question Answering2022-05-05