Multi-objects Generation with Amortized Structural Regularization

Authors: Taufik Xu, Chongxuan LI, Jun Zhu, Bo Zhang

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

Reproducibility Variable Result LLM Response
Research Type Experimental Empirical results show that ASR outperforms the DGM baselines in terms of inference performance and sample quality.
Researcher Affiliation Academia Kun Xu, Chongxuan Li, Jun Zhu , Bo Zhang Dept. of Comp. Sci. & Tech., Institute for AI, THBI Lab, BNRist Center, State Key Lab for Intell. Tech. & Sys., Tsinghua University, Beijing, China {kunxu.thu, chongxuanli1991}@gmail.com, {dcszj, dcszb}@tsinghua.edu.cn
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks (clearly labeled algorithm sections or code-like formatted procedures).
Open Source Code Yes Our code is attached in the supplementary materials for reproducing.
Open Datasets Yes In this section, we present the empirical results of ASR on two dataset: Multi-MNIST [8] and Multi-Sprites [12]
Dataset Splits No The paper specifies training and test data sizes (e.g., '40000 training samples' and '2000 images are used as the test data'), but it does not explicitly state a validation dataset split.
Hardware Specification No The paper mentions implementing the model using TensorFlow but provides no specific details about the hardware used for running experiments, such as GPU/CPU models or memory specifications.
Software Dependencies No We implement our model using Tenwor Flow [1] library. (The paper mentions 'Tenwor Flow' but does not specify a version number for this or any other software dependency.)
Experiment Setup Yes We use the Adam optimizer [18] with learning rate as 0.001, β1 = 0.9, and β2 = 0.999. We train models with 300 epochs with batch size as 64.