Methods › General › Out-of-Distribution Example Detection › DIME
Distance to Modelled Embedding
DIME
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
DIME, or Distance to Modelled Embedding, is a method for detecting out-of-distribution examples during prediction time. Given a trained neural network, the training data drawn from some high-dimensional distribution in data space X is transformed into the model’s intermediate feature vector space ℝᵖ. The training set embedding is linearly approximated as a hyperplane. When we then receive new observations it is difficult to assess if observations are out-of-distribution directly in data space, so we transform them into the same intermediate feature space. Finally, the Distance-to-Modelled-Embedding (DIME) can be used to assess whether new observations fit into the expected embedding covariance structure.
Papers archive 2025-07-28
5 shown of 5, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
DIME:Diffusion-Based Maximum Entropy Reinforcement Learning 4 Feb 2025 · 0 repositories · arXiv:2502.02316
-
Dexterous Imitation Made Easy: A Learning-Based Framework for Efficient Dexterous Manipulation 24 Mar 2022 · 0 repositories · arXiv:2203.13251
-
DIME: Fine-grained Interpretations of Multimodal Models via Disentangled Local Explanations 3 Mar 2022 · 1 repository · arXiv:2203.02013Syntology ran 5 of 7 samples · 2 unverified
-
Rethnicity: Predicting Ethnicity from Names 19 Sep 2021 · 1 repository · arXiv:2109.09228
-
Out-of-Distribution Example Detection in Deep Neural Networks using Distance to Modelled Embedding 24 Aug 2021 · 1 repository · arXiv:2108.10673
Tasks archive 2025-07-28
8 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| Decision Making | 1 |
| Disentanglement | 1 |
| Imitation Learning | 1 |
| Prediction | 1 |
| Reinforcement Learning | 1 |
| Time Series | 1 |
| Time Series Analysis | 1 |
| reinforcement-learning | 1 |
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