Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userDifference-in-Differences: Bridging Normalization and Disentanglement in PG-GAN
99
0
0.0
(
0
)
Added by
Xiao Liu
Publication date
2020
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
What mechanisms causes GANs entanglement? Although developing disentangled GAN has attracted sufficient attention, it is unclear how entanglement is originated by GAN transformation. We in this research propose a difference-in-difference (DID) counterfactual framework to design experiments for analyzing the entanglement mechanism in on of the Progressive-growing GAN (PG-GAN). Our experiment clarify the mechanisms how pixel normalization causes PG-GAN entanglement during a input-unit-ablation transformation. We discover that pixel normalization causes object entanglement by in-painting the area occupied by ablated objects. We also discover the unit-object relation determines whether and how pixel normalization causes objects entanglement. Our DID framework theoretically guarantees that the mechanisms that we discover is solid, explainable and comprehensively.
rate research
Read More
Batch normalization has been widely used to improve optimization in deep neural networks. While the uncertainty in batch statistics can act as a regularizer, using these dataset statistics specific to the training set impairs generalization in certain tasks. Recently, alternative methods for normalizing feature activations in neural networks have been proposed. Among them, group normalization has been shown to yield similar, in some domains even superior performance to batch normalization. All these methods utilize a learned affine transformation after the normalization operation to increase representational power. Methods used in conditional computation define the parameters of these transformations as learnable functions of conditioning information. In this work, we study whether and where the conditional formulation of group normalization can improve generalization compared to conditional batch normalization. We evaluate performances on the tasks of visual question answering, few-shot learning, and conditional image generation.
One of the important research topics in image generative models is to disentangle the spatial contents and styles for their separate control. Although StyleGAN can generate content feature vectors from random noises, the resulting spatial content control is primarily intended for minor spatial variations, and the disentanglement of global content and styles is by no means complete. Inspired by a mathematical understanding of normalization and attention, here we present a novel hierarchical adaptive Diagonal spatial ATtention (DAT) layers to separately manipulate the spatial contents from styles in a hierarchical manner. Using DAT and AdaIN, our method enables coarse-to-fine level disentanglement of spatial contents and styles. In addition, our generator can be easily integrated into the GAN inversion framework so that the content and style of translated images from multi-domain image translation tasks can be flexibly controlled. By using various datasets, we confirm that the proposed method not only outperforms the existing models in disentanglement scores, but also provides more flexible control over spatial features in the generated images.
Recent work has highlighted the difficulties of estimating difference-in-differences models when treatment timing occurs at different times for different units. This article introduces the R package did2s which implements the estimator introduced in Gardner (2021). The article provides an approachable review of the underlying econometric theory and introduces the syntax for the function did2s. Further, the package introduces a function, event_study, that provides a common syntax for all the modern event-study estimators and plot_event_study to plot the results of each estimator.
Empirical work often uses treatment assigned following geographic boundaries. When the effects of treatment cross over borders, classical difference-in-differences estimation produces biased estimates for the average treatment effect. In this paper, I introduce a potential outcomes framework to model spillover effects and decompose the estimates bias in two parts: (1) the control group no longer identifies the counterfactual trend because their outcomes are affected by treatment and (2) changes in treated units outcomes reflect the effect of their own treatment status and the effect from the treatment status of close units. I propose estimation strategies that can remove both sources of bias and semi-parametrically estimate the spillover effects themselves. I extend Callaway and SantAnna (2020) to allow for event-study estimates that control for spillovers. To highlight the importance of spillover effects, I revisit analyses of three place-based interventions.
Empirical works suggest that various semantics emerge in the latent space of Generative Adversarial Networks (GANs) when being trained to generate images. To perform real image editing, it requires an accurate mapping from the real image to the latent space to leveraging these learned semantics, which is important yet difficult. An in-domain GAN inversion approach is recently proposed to constraint the inverted code within the latent space by forcing the reconstructed image obtained from the inverted code within the real image space. Empirically, we find that the inverted code by the in-domain GAN can deviate from the latent space significantly. To solve this problem, we propose a force-in-domain GAN based on the in-domain GAN, which utilizes a discriminator to force the inverted code within the latent space. The force-in-domain GAN can also be interpreted by a cycle-GAN with slight modification. Extensive experiments show that our force-in-domain GAN not only reconstructs the target image at the pixel level, but also align the inverted code with the latent space well for semantic editing.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
