Hold me tight! Influence of discriminative features on deep network boundaries

Authors: Guillermo Ortiz-Jimenez, Apostolos Modas, Seyed-Mohsen Moosavi, Pascal Frossard

NeurIPS 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We empirically support our findings by extensive evaluations on both synthetic and real datasets.
Researcher Affiliation Academia Guillermo Ortiz-Jiménez EPFL, Lausanne, Switzerland guillermo.ortizjimenez@epfl.ch Apostolos Modas EPFL, Lausanne, Switzerland apostolos.modas@epfl.ch Seyed-Mohsen Moosavi-Dezfooli ETH Zürich, Zurich, Switzerland seyed.moosavi@inf.ethz.ch Pascal Frossard EPFL, Lausanne, Switzerland pascal.frossard@epfl.ch
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code Yes The code to reproduce our experiments can be found at https://github.com/LTS4/hold-me-tight.
Open Datasets Yes In our study, we train multiple networks on MNIST [25] and CIFAR-10 [26], and for Image Net [27] we use several of the pretrained networks provided by Py Torch [28]5.
Dataset Splits No The paper mentions training and test sets, but does not explicitly provide details about validation set splits needed for reproduction.
Hardware Specification No The paper does not provide specific hardware details (exact GPU/CPU models, processor types with speeds, memory amounts, or detailed computer specifications) used for running its experiments.
Software Dependencies No The paper mentions PyTorch [28] but does not provide specific version numbers for software dependencies.
Experiment Setup No The paper mentions general training details like using SGD and cross-entropy loss, but it does not provide specific hyperparameter values or comprehensive training configurations in the main text needed for exact reproduction.