ChimeraMix: Image Classification on Small Datasets via Masked Feature Mixing
Authors: Christoph Reinders, Frederik Schubert, Bodo Rosenhahn
IJCAI 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | For evaluation, all methods are trained from scratch without any additional data. Several experiments on benchmark datasets, e.g., ci FAIR-10, STL-10, and ci FAIR-100, demonstrate the superior performance of Chimera Mix compared to current state-of-the-art methods for classification on small datasets. |
| Researcher Affiliation | Academia | Christoph Reinders , Frederik Schubert and Bodo Rosenhahn Institute for Information Processing, Leibniz University Hannover {reinders,schubert,rosenhahn}@tnt.uni-hannover.de |
| Pseudocode | No | The paper does not contain any clearly labeled pseudocode or algorithm blocks. |
| Open Source Code | Yes | Code is available at https://github.com/creinders/Chimera Mix. |
| Open Datasets | Yes | For our experiments, we choose the ci FAIR-10 and ci FAIR100 [Barz and Denzler, 2020b] datasets. Both contain 50,000 and 10,000 images of size 32 32 in their training and test set and have been extensively used in computer vision research2. Lastly, we evaluate our method on STL-10 [Coates et al., 2011] which is a slightly more complex dataset consisting of 5000 training and 8000 test images of size 96 96 from 10 categories. |
| Dataset Splits | No | The paper mentions 'training and test set' for datasets and 'validation accuracy', but does not explicitly provide specific details (e.g., percentages, sample counts, or methodology) for a dedicated validation split to reproduce the data partitioning. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., GPU/CPU models, memory amounts, or detailed computer specifications) used for running its experiments. |
| Software Dependencies | No | The paper does not provide specific ancillary software details (e.g., library or solver names with version numbers) needed to replicate the experiment. |
| Experiment Setup | No | The paper states: 'The hyperparameters can be found in the supplementary material.' This indicates that the specific experimental setup details are not provided in the main text. |