Unsupervised Attention-guided Image-to-Image Translation

Authors: Youssef Alami Mejjati, Christian Richardt, James Tompkin, Darren Cosker, Kwang In Kim

NeurIPS 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We demonstrate qualitatively and quantitatively that our approach attends to relevant regions in the image without requiring supervision, which creates more realistic mappings when compared to those of recent approaches.
Researcher Affiliation Academia Youssef A. Mejjati University of Bath yam28@bath.ac.uk Christian Richardt University of Bath christian@richardt.name James Tompkin Brown University james_tompkin@brown.edu Darren Cosker University of Bath D.P.Cosker@bath.ac.uk Kwang In Kim University of Bath k.kim@bath.ac.uk
Pseudocode Yes Algorithm 1 summarizes the training procedure for learning FS T ; training FT S is similar.
Open Source Code Yes Our code is released in the following Github repository: https://github.com/Alami Mejjati/Unsupervised-Attention-guided-Image-to-Image-Translation.
Open Datasets Yes We use the Apple to Orange (A O) and Horse to Zebra (H Z) datasets provided by Zhu et al. [1], and the Lion to Tiger (L T) dataset obtained from the corresponding classes in the Animals With Attributes (AWA) dataset [28].
Dataset Splits No The paper mentions training and testing but does not provide specific details on training/test/validation dataset splits (e.g., percentages or counts) or their methodology.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory specifications) used for running experiments.
Software Dependencies No The paper does not provide specific software dependencies with version numbers (e.g., library names like PyTorch, TensorFlow, or Python versions).
Experiment Setup Yes where we use the loss hyper-parameter λcyc = 10 throughout our experiments.Algorithm 1 summarizes the training procedure... K (number of epochs), λcyc (cycle-consistency weight), α (ADAM learning rate).we first train the discriminators on full images for 30 epochs.which we set to 0.1.