[ILSVRC, visual transformers] Data for "Exploring specialization and sensitivity of convolutional neural networks in the context of simultaneous image augmentations"

This repository contains data collected under the following study:P.Kharyuk, S.Matveev, I.Oseledets. Exploring specialization and sensitivity of convolutional neural networks in the context of simultaneous image augmentations, arXiv:2503.03283. Corresponding source code repository: https://github.com/kharyuk/activation_sa CNNs: ILSVRC: 10.5281/zenodo.18097911 Places365: 10.5281/zenodo.18098133 0_models.7z: copy of the visual transformer models (ViT-b-16, Swin-t, MaxViT-t) used in the research (reference: https://docs.pytorch.org/vision/main/models.html) 1_sensitivity_values.7z: sensitivity values (Sobol indices, Shapley values) computed for the first experimental series (ViT-b-16, Swin-t). In addition, logs and npz-files containing the sampled parameters were packed. To be used within the jupyter notebooks, all .hdf5 files should be placed into the 'results' directory of the source code repository. 2a_predictions.7z: these files include the top-5 class predictions and corresponding classifying layer's outputs used for evaluating Table 1 (ViT-b-16, Swin-t, MaxViT-t). SupplementaryS3.7z: Supplementary material containing visualized sensitivity maps (Vit-b-16, Swin-t).