Learning Multimodal VAEs through Mutual Supervision
Authors: Tom Joy, Yuge Shi, Philip Torr, Tom Rainforth, Sebastian M Schmon, Siddharth N
ICLR 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We demonstrate that MEME outperforms baselines on standard metrics across both partial and complete observation schemes on the MNIST-SVHN (image image) and CUB (image text) datasets. |
| Researcher Affiliation | Academia | 1University of Oxford 2University of Durham 3University of Edinburgh & The Alan Turing Institute |
| Pseudocode | No | The paper does not contain any pseudocode or clearly labeled algorithm blocks. |
| Open Source Code | Yes | The codebase is available at the following location: https://github.com/thwjoy/meme. |
| Open Datasets | Yes | We demonstrate our results on two datasets, namely an image image dataset MNIST-SVHN (Le Cun et al., 2010; Netzer et al., 2011); as well as the more challenging, but less common, image caption dataset CUB (Welinder et al., 2010). |
| Dataset Splits | No | The paper describes different proportions of partial observations used during training (e.g., f=1.0, f<1.0), but it does not specify a conventional train/validation/test split with exact percentages, sample counts, or references to predefined splits for reproducibility. |
| Hardware Specification | No | The paper mentions memory consumption during training ("training consumed around 2Gb of memory" and "3Gb of memory") but does not specify any particular hardware components like GPU or CPU models. |
| Software Dependencies | No | The paper mentions that architectures "can easily be implemented in popular deep learning frameworks such as Pytorch and Tensorflow" but does not provide specific version numbers for these or any other software dependencies. |
| Experiment Setup | Yes | We used the Adam optimizer with a learning rate of 0.0005 and beta values of (0.9, 0.999) for 100 epochs... We used the Adam optimizer with a learning rate of 0.0001 and beta values of (0.9, 0.999) for 300 epochs. |