Adversarial Self-Defense for Cycle-Consistent GANs

Authors: Dina Bashkirova, Ben Usman, Kate Saenko

NeurIPS 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We perform a quantitative evaluation of the proposed techniques and show that making the translation model more robust to the self-adversarial attack increases its generation quality and reconstruction reliability and makes the model less sensitive to low-amplitude perturbations. Our project page can be found at ai.bu.edu/selfadv/. 5 Experiments and results
Researcher Affiliation Collaboration Dina Bashkirova 1, Ben Usman1, and Kate Saenko 1,2 1Boston University 2MIT-IBM Watson AI Lab
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code No Our project page can be found at ai.bu.edu/selfadv/. This is a project page, not a direct link to a source code repository or an explicit statement about code availability.
Open Datasets Yes To provide empirical evidence of our claims, we performed a sequence of experiments on three publicly available image-to-image translation datasets. ... Google Aerial Photo to Maps dataset consisting of 3292 pairs of aerial photos and corresponding maps. ... The dataset is available at [6]. ... Playing for Data (GTA)[26] dataset ... Syn Action [28] synthetic human action dataset
Dataset Splits No We used 1098 images for training and 1096 images for testing. ... 7500 images for training, 2500 images for testing ... 1561 images in each domain for training 357 images for testing. The paper specifies training and testing splits but does not explicitly mention a validation split.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory) used for running the experiments.
Software Dependencies No The details on model architectures and choice of hyperparameters used in our experiments can be found in the supplementary materials. The main paper text does not list specific software dependencies with version numbers.
Experiment Setup No The details on model architectures and choice of hyperparameters used in our experiments can be found in the supplementary materials. The main paper text does not provide specific experimental setup details like hyperparameter values or training configurations.