Adaptive Density Estimation for Generative Models

Authors: Thomas Lucas, Konstantin Shmelkov, Karteek Alahari, Cordelia Schmid, Jakob Verbeek

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

Reproducibility Variable Result LLM Response
Research Type Experimental We experimentally validate our approach on the CIFAR-10 dataset with an ablation study. Our model significantly improves over existing hybrid models, producing GAN-like samples, and IS and FID scores that are competitive with fully adversarial models, see Figure 3. At the same time, we obtain likelihoods on held-out data comparable to state-of-the-art likelihood-based methods which requires covering the full support of the dataset. We further confirm these observations with quantitative and qualitative experimental results on the STL-10, Image Net and LSUN datasets.
Researcher Affiliation Collaboration Thomas Lucas Inria Konstantin Shmelkov , Noah s Ark Lab, Huawei Cordelia Schmid Inria Karteek Alahari Inria Jakob Verbeek Inria
Pseudocode Yes The training procedure, written as an algorithm in Appendix H, alternates between (i) bringing LQ(pθ,ψ) closer to it s optimal value L Q(pθ,ψ) = DKL(pθ,ψ||p ), and (ii) minimizing LC(pθ,ψ)+LQ(pθ,ψ).
Open Source Code No The paper does not provide a direct link to open-source code or explicitly state that the code for the methodology is available.
Open Datasets Yes We experimentally validate our approach on the CIFAR-10 dataset with an ablation study... We further confirm these observations with quantitative and qualitative experimental results on the STL-10, Image Net and LSUN datasets.
Dataset Splits No We use the standard split of 50k/10k train/test images of 32 32 pixels.
Hardware Specification Yes Figure 7 shows samples from our generator trained on a single GPU with 11 Gb of memory on LSUN classes.
Software Dependencies No The paper mentions optimizers like Adam but does not provide specific version numbers for software dependencies or libraries used.
Experiment Setup No The paper describes model architectures and training objectives but does not provide specific hyperparameter values like learning rate, batch size, or number of epochs in the main text.