paper-with-me

Papers

Visualizing and Understanding GANs

2019-03-27 · ICLR Workshop DeepGenStruct 2019 · David Bau, Jun-Yan Zhu, Hendrik Strobelt, Bolei Zhou, Joshua B. Tenenbaum, William T. Freeman, Antonio Torralba

We present an analytic framework to visualize and understand GANs at the unit-, object-, and scene-level. We first identify a group of interpretable units that are closely related to object concepts with a segmentation-based network dissection method. Then, we examine the causal effect of interpretable units by measuring the ability of interventions to control objects in the output. Finally, we examine the contextual relationship between these units and their surrounding by inserting the discovered object concepts into new images. We show several practical applications enabled by our framework, from comparing internal representations across different layers and models, to improving GANs by locating and removing artifact-causing units, to interactively manipulating objects in the scene.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Object

Similar Papers 제목 키워드 기반

Visualizing chest X-ray dataset biases using GANs

2023-04-29 · Hao Liang, Kevin Ni, Guha Balakrishnan

Recent work demonstrates that images from various chest X-ray datasets contain visual features that are strongly correlated with protected demographic attributes like race and gender. This finding raises issues of fairne…

Fairness

GAN Dissection: Visualizing and Understanding Generative Adversarial Networks

2018-11-26 · ICLR 2019 5 · David Bau, Jun-Yan Zhu, Hendrik Strobelt, Bolei Zhou 외

Generative Adversarial Networks (GANs) have recently achieved impressive results for many real-world applications, and many GAN variants have emerged with improvements in sample quality and training stability. However, t…

Image GenerationObject

Visualizing the Consequences of Climate Change Using Cycle-Consistent Adversarial Networks

2019-05-02 · Victor Schmidt, Alexandra Luccioni, S. Karthik Mukkavilli, Narmada Balasooriya 외

We present a project that aims to generate images that depict accurate, vivid, and personalized outcomes of climate change using Cycle-Consistent Adversarial Networks (CycleGANs). By training our CycleGAN model on street…

ST-GAN: Spatial Transformer Generative Adversarial Networks for Image Compositing

2018-03-05 · CVPR 2018 6 · Chen-Hsuan Lin, Ersin Yumer, Oliver Wang, Eli Shechtman 외

We address the problem of finding realistic geometric corrections to a foreground object such that it appears natural when composited into a background image. To achieve this, we propose a novel Generative Adversarial Ne…

Generative Adversarial Network

Visualizing the Flow of Discourse with a Concept Ontology

2018-02-23 · Baoxu Shi, Tim Weninger

Understanding and visualizing human discourse has long being a challenging task. Although recent work on argument mining have shown success in classifying the role of various sentences, the task of recognizing concepts a…

Argument Mining