Methods › Computer Vision › Generative Models › Contractive Autoencoder
Contractive Autoencoder
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
A Contractive Autoencoder is an autoencoder that adds a penalty term to the classical reconstruction cost function. This penalty term corresponds to the Frobenius norm of the Jacobian matrix of the encoder activations with respect to the input. This penalty term results in a localized space contraction which in turn yields robust features on the activation layer. The penalty helps to carve a representation that better captures the local directions of variation dictated by the data, corresponding to a lower-dimensional non-linear manifold, while being more invariant to the vast majority of directions orthogonal to the manifold.
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.
-
Scalable Self-Supervised Representation Learning from Spatiotemporal Motion Trajectories for Multimodal Computer Vision 7 Oct 2022 · 0 repositories · arXiv:2210.03289
-
Reachability Embeddings: Scalable Self-Supervised Representation Learning from Mobility Trajectories for Multimodal Geospatial Computer Vision 24 Oct 2021 · 0 repositories · arXiv:2110.12521
-
Predicting Sample Collision with Neural Networks 30 Jun 2020 · 0 repositories · arXiv:2006.16868
-
Majorization Minimization Technique for Optimally Solving Deep Dictionary Learning 11 Dec 2019 · 0 repositories · arXiv:1912.10801
-
Towards Deep Neural Network Architectures Robust to Adversarial Examples 11 Dec 2014 · 2 repositories · arXiv:1412.5068Syntology ran 1 of 2 samples · 1 unverified
Tasks archive 2025-07-28
5 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 |
|---|---|
| Denoising | 2 |
| Representation Learning | 2 |
| Semantic Segmentation | 2 |
| Dictionary Learning | 1 |
| Motion Planning | 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