SimMMDG: A Simple and Effective Framework for Multi-modal Domain Generalization

Authors: Hao Dong, Ismail Nejjar, Han Sun, Eleni Chatzi, Olga Fink

NeurIPS 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We demonstrate that our framework is theoretically well-supported and achieves strong performance in multi-modal DG on the EPIC-Kitchens dataset and the novel Human-Animal-Cartoon (HAC) dataset introduced in this paper.
Researcher Affiliation Academia 1ETH Zürich 2EPFL
Pseudocode No The paper describes its methodology in natural language and diagrams, but does not include any structured pseudocode or algorithm blocks.
Open Source Code Yes Our source code and HAC dataset are available at https://github.com/donghao51/Sim MMDG.
Open Datasets Yes We use the EPIC-Kitchens dataset [16] and introduce a novel HAC dataset in this paper, which will be made publicly accessible for further research. ... Our source code and HAC dataset are available at https://github.com/donghao51/Sim MMDG.
Dataset Splits Yes We train the network for 15 epochs on an RTX 2080 Ti GPU which takes about 20 hours and select the model with the best performance on the validation dataset.
Hardware Specification Yes Finally, we train the network for 15 epochs on an RTX 2080 Ti GPU which takes about 20 hours and select the model with the best performance on the validation dataset.
Software Dependencies No The paper mentions using 'MMAction2 toolkit' and 'Adam optimizer' but does not provide specific version numbers for software dependencies like PyTorch, TensorFlow, CUDA, or the MMAction2 toolkit itself.
Experiment Setup Yes We use the Adam optimizer [39] with a learning rate of 0.0001 and a batch size of 16. The scalar temperature parameter τ is set to 0.1. Additionally, we set αcon = 3.0, αdis = 0.7, and αtrans = 0.1. ... Finally, we train the network for 15 epochs...