Investigating object compositionality in Generative Adversarial Networks.
Reads0
Chats0
TLDR
In this article, the authors investigate object compositionality as an inductive bias for Generative Adversarial Networks (GANs) and propose two useful extensions to incorporate dependencies among objects and background.About:
This article is published in Neural Networks.The article was published on 2020-07-13 and is currently open access. It has received 25 citations till now. The article focuses on the topics: Generative model & Inductive bias.read more
Citations
More filters
Posted Content
GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields
Michael Niemeyer,Andreas Geiger +1 more
TL;DR: The key hypothesis is that incorporating a compositional 3D scene representation into the generative model leads to more controllable image synthesis and a fast and realistic image synthesis model is proposed.
Proceedings ArticleDOI
GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields
Michael Niemeyer,Andreas Geiger +1 more
TL;DR: In this paper, a compositional generative neural feature field is proposed to disentangle one or multiple objects from the background as well as individual objects' shapes and appearances while learning from unstructured and unposed image collections without any additional supervision.
Posted Content
On the Binding Problem in Artificial Neural Networks.
TL;DR: This paper proposes a unifying framework that revolves around forming meaningful entities from unstructured sensory inputs, maintaining this separation of information at a representational level (representation), and using these entities to construct new inferences, predictions, and behaviors (composition).
Journal ArticleDOI
Advances in Data Preprocessing for Biomedical Data Fusion: An Overview of the Methods, Challenges, and Prospects
Shuihua Wang,M. Emre Celebi,Yudong Zhang,Xiang Yu,Siyuan Lu,Xujing Yao,Qinghua Zhou,Martínez-García Miguel,Yingli Tian,Juan Manuel Górriz,Ivan Tyukin +10 more
TL;DR: An overview of the advances in data preprocessing in biomedical data fusion is provided in this article, along with insights stemming from new developments in the field, and an overview of new techniques for data fusion methods are discussed.
Posted Content
Unsupervised Object Segmentation by Redrawing
TL;DR: ReDO is presented, a new model able to extract objects from images without any annotation in an unsupervised way based on the idea that it should be possible to change the textures or colors of the objects without changing the overall distribution of the dataset.
References
More filters
Proceedings Article
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
TL;DR: This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
Proceedings Article
Attention is All you Need
Ashish Vaswani,Noam Shazeer,Niki Parmar,Jakob Uszkoreit,Llion Jones,Aidan N. Gomez,Lukasz Kaiser,Illia Polosukhin +7 more
TL;DR: This paper proposed a simple network architecture based solely on an attention mechanism, dispensing with recurrence and convolutions entirely and achieved state-of-the-art performance on English-to-French translation.
Journal ArticleDOI
Gradient-based learning applied to document recognition
Yann LeCun,Léon Bottou,Léon Bottou,Yoshua Bengio,Yoshua Bengio,Yoshua Bengio,Patrick Haffner +6 more
TL;DR: In this article, a graph transformer network (GTN) is proposed for handwritten character recognition, which can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters.
Journal ArticleDOI
Generative Adversarial Nets
Ian Goodfellow,Jean Pouget-Abadie,Mehdi Mirza,Bing Xu,David Warde-Farley,Sherjil Ozair,Aaron Courville,Yoshua Bengio +7 more
TL;DR: A new framework for estimating generative models via an adversarial process, in which two models are simultaneously train: a generative model G that captures the data distribution and a discriminative model D that estimates the probability that a sample came from the training data rather than G.
Dissertation
Learning Multiple Layers of Features from Tiny Images
TL;DR: In this paper, the authors describe how to train a multi-layer generative model of natural images, using a dataset of millions of tiny colour images, described in the next section.