Counterfactual Image Editing

Authors: Yushu Pan, Elias Bareinboim

ICML 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental In this section, we conduct an empirical evaluation of the method newly proposed, first with a modified Colored MNIST dataset (Section 5.1) and then with the Celeb AHQ dataset (Karras et al., 2018) (which describes peoples faces) (Section 5.2). More experiments and further details of the model architectures are provided in Appendix B.
Researcher Affiliation Academia 1Department of Computer Science, Columbia University, New York, USA. Correspondence to: Yushu Pan <yushupan@cs.columbia.edu>.
Pseudocode No The paper mentions developing an efficient algorithm (ANCMs) but does not provide a formal pseudocode block or algorithm listing within the main text.
Open Source Code No The paper does not provide any explicit statements about open-sourcing code or links to a code repository for the methodology described.
Open Datasets Yes We first conduct experiments on the modified handwritten MNIST dataset (Deng, 2012), featuring colored digits and a horizontal blue bar in images. ... In Celeb A-HQ experiment, we consider two causal diagrams as shown in Fig. 6. ... Celeb AHQ dataset (Karras et al., 2018)
Dataset Splits No The paper describes the training process and objectives, but does not explicitly state the specific dataset splits (e.g., percentages or sample counts) for training, validation, or testing within the main text.
Hardware Specification No The paper does not provide any specific details regarding the hardware (e.g., CPU, GPU models, memory, or cloud instances) used for running the experiments.
Software Dependencies No The paper mentions the use of 'Neural Causal Model (NCM)', 'Diffuse VAE', and refers to 'VAE' and 'CVAE' in comparisons. It also cites papers for tools like 'Adam' and 'pytorch' (Paszke et al., 2017). However, it does not specify version numbers for these software dependencies, which is required for reproducible description.
Experiment Setup No The paper states that 'More details about the architecture and hyperparameters can be found in Appendix B.1.3.'. However, the main text itself does not provide specific hyperparameter values or detailed system-level training settings.