Supplementary materials for: Plug & Play Generative Networks: Conditional Iterative Generation of Images in Latent Space

2017

Subfields: Generative Models

Citations in the corpus

• Learning General Purpose Distributed Sentence Representations via Large Scale Multi-task Learning (2018, background): “Having a rich, continuous sentence representation space could allow the application of state-of-the-art generative models of images such as that of Nguyen et al. (2016) to language.”
• Making Convolutional Networks Shift-Invariant Again (2019, background): “…hidden units (Girshick et al., 2014; Zhou et al., 2015), actively maximizing hidden units (Mordvintsev et al., 2015), and mapping features back into pixel space (Zeiler & Fergus, 2014; H´enaff & Si-moncelli, 2016; Mahendran & Vedaldi, 2015; Dosovitskiy & Brox, 2016a;b; Nguyen et al., 2017).”
• Strike (With) a Pose: Neural Networks Are Easily Fooled by Strange Poses of Familiar Objects (2018, background): “But pixel-wise changes are uncorrelated [28], so pixel-based attacks may not transfer well to the real world [24, 26] because there is an infinitesimal chance that such specifically crafted, uncorrelated pixels will be encountered in the vast physical space of camera, lighting, traffic, and weather ”
• Zero-Shot Text-to-Image Generation (2021, neutral): “Separately, Nguyen et al. (2017) propose an energy-based framework for conditional image generation that obtained a large improvement in sample quality relative to contemporary methods.”
• Your GAN is Secretly an Energy-based Model and You Should use Discriminator Driven Latent Sampling (2020, background): “Generative Adversarial Networks (GANs) [3] are state-of-the-art models for a large variety of tasks such as image generation [4], semi-supervised learning [5], image editing [6], image translation [7], and imitation learning [8].”
• Projected GANs Converge Faster (2021, neutral): “Pretrained models can be used as a guiding mechanism to disentangle causal generative factors [54], for text-driven image manipulation [44], matching the generator activations to inverted classifiers [19, 56], or to generate images via gradient ascent in the latent space of a generator [41].”
• CLIPDraw: Exploring Text-to-Drawing Synthesis through Language-Image Encoders (2021, background): “…is that the produced images often leave the space of natural images (Nguyen et al., 2015), or fool the system through adversarial means (Goodfellow et al., 2014b), thus a body of work aims to discover ‘natural image priors’ to constrain which images may be produced (Nguyen et al., 2016; 2017).”
• D2C: Diffusion-Decoding Models for Few-Shot Conditional Generation (2021, methodology): “The disciminative model can operate on either the image space [66, 70, 27] or the latent space [80, 98].”
• Symbolic Music Generation with Diffusion Models (2021, background): “Conditional sampling from unconditional models: We build on top of the breadth of material that explores conditional sampling from unconditionally trained models by using an additional model to steer generation in the latent space of an unconditionally trained generative model (Nguyen et al., 2017; ”
• High Fidelity Visualization of What Your Self-Supervised Representation Knows About (2021, background): “The following work (Nguyen et al., 2017) demonstrates how using this conditional iterative optimization in the latent space of the generator lead to high quality conditional image generation.”
• Cross-Modal Contrastive Learning for Text-to-Image Generation (2021, methodology): “Text-to-image synthesis Generating images from text descriptions has been quickly improved with deep generative models, including pixelCNN [55, 45], approximate Langevin sampling [34], variational autoencoders (VAEs) [21, 13] and Generative Adversarial Networks (GANs) [12, 44].”
• DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-To-Image Synthesis (2019, background): “Dataset GAN-INT-CLS [20] GAWWN [21] StackGAN [30] PPGN [16] AttnGAN [28] DM-GAN”
• AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks (2017, methodology): “Then, we compare our AttnGAN with previous state-of-the-art GAN models for textto-image synthesis [36, 37, 20, 18, 16].”
• Plug and Play Language Models: A Simple Approach to Controlled Text Generation (2019, methodology): “In computer vision, Plug & Play Generative Networks (PPGN) from Nguyen et al. (2017) developed a mechanism for generating images with different attributes by plugging a discriminator (attribute model) p ( a | x ) together with a base generative model p ( x ) and sampling from the resulting p ( x |…”
• Gradient descent GAN optimization is locally stable (2017, methodology): “…deployed for tasks such as photo super-resolution, object generation, video prediction, language modeling, vocal synthesis, and semi-supervised learning, amongst many others [Ledig et al., 2016, Wu et al., 2016, Mathieu et al., 2015, Nguyen et al., 2016, Denton et al., 2015, Im et al., 2016].”
• Unsupervised Image-to-Image Translation Networks (2017, neutral): “, 2016), and Plug&Play Generative Networks (Nguyen et al., 2016).”
• Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks (2017, background): “…Pixel-RNNs (van den Oord et al., 2016b), PixelCNNs (van den Oord et al., 2016a), real NVP (Dinh et al., 2016) and Plug & Play generative networks (Nguyen et al., 2016) have been introduced and studied, the two most prominent ones are Variational Autoencoders (VAEs) (Kingma & Welling, 2013;…”
• Feature Purification: How Adversarial Training Performs Robust Deep Learning (2020, neutral): “using GAN) to capture the prior [70, 73, 74].”