Topographic VAEs learn Equivariant Capsules
Authors: T. Anderson Keller, Max Welling
NeurIPS 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | In the following experiments, we demonstrate the viability of the Topographic VAE as a novel method for training deep topographic generative models. Additionally, we quantitatively verify that shifting temporal coherence yields approximately equivariant capsules by computing an equivariance loss and a correlation metric inspired by the disentanglement literature. We show that equivariant capsule models yield higher likelihood than baselines on test sequences, and qualitatively support these results with visualizations of sequences reconstructed purely from Rolled capsule activations. |
| Researcher Affiliation | Collaboration | T. Anderson Keller Uv A-Bosch Delta Lab University of Amsterdam t.anderson.keller@gmail.com Max Welling Uv A-Bosch Delta Lab University of Amsterdam m.welling@uva.nl |
| Pseudocode | No | The paper does not contain structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide concrete access to source code for the methodology described in this paper. It mentions using PyTorch but not releasing their own code. |
| Open Datasets | Yes | We arrange the latent space into 15 circular capsules each of 15-dimensions for d Sprites [43], and 18 circular capsules each of 18-dimensions for MNIST [37]. |
| Dataset Splits | No | The paper mentions 'test sequences' and 'test data' but does not provide specific dataset split information (exact percentages, sample counts, citations to predefined splits, or detailed splitting methodology) for training, validation, and testing. |
| Hardware Specification | No | The paper does not provide specific hardware details used for running its experiments. |
| Software Dependencies | No | The paper mentions using 'PyTorch [47]' and 'Weight & Biases [5]' but does not provide specific version numbers for these software components. |
| Experiment Setup | No | The paper describes the model architecture (3-layer MLP with ReLU), capsule dimensions, and types of transformations, but does not provide specific experimental setup details such as concrete hyperparameter values (e.g., learning rate, batch size, number of epochs, optimizer settings) in the main text. |