Adversarial Scene Editing: Automatic Object Removal from Weak Supervision

Authors: Rakshith R. Shetty, Mario Fritz, Bernt Schiele

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

Reproducibility Variable Result LLM Response
Research Type Experimental We experimentally show on two datasets that our method effectively removes a wide variety of objects using weak supervision only.
Researcher Affiliation Academia 1Max Planck Institute for Informatics, Saarland Informatics Campus 2CISPA Helmholtz Center i.G., Saarland Informatics Campus Saarbrücken, Germany
Pseudocode No The paper describes the model and optimization process in text and equations but does not include any clearly labeled “Pseudocode” or “Algorithm” blocks.
Open Source Code No The paper does not provide an explicit statement about releasing source code or a link to a code repository.
Open Datasets Yes we train and test our model mainly on the COCO dataset [9]... We use the segmentation masks from Pascal-VOC 2012 dataset [27]... We use the Flickr Logos dataset [28]
Dataset Splits No The paper mentions training and testing on datasets like COCO, Pascal-VOC, and Flickr Logos, but it does not specify explicit dataset splits (e.g., percentages or counts for training, validation, and test sets) needed for reproduction.
Hardware Specification No The paper does not provide specific hardware details such as GPU models, CPU types, or memory amounts used for running the experiments.
Software Dependencies No The paper does not provide specific ancillary software details with version numbers (e.g., libraries or frameworks like PyTorch or TensorFlow versions, or specific solver versions) needed to replicate the experiment.
Experiment Setup No The paper describes the loss functions and optimization strategy (“optimized in alternate epochs using gradient descent”) but does not provide specific concrete hyperparameter values (e.g., learning rates, batch sizes, values for λc, λp, etc.) or detailed training configurations in the main text.