paper-with-me

Papers

Positional Encoding as Spatial Inductive Bias in GANs

2020-12-09 · CVPR 2021 1 · Rui Xu, Xintao Wang, Kai Chen, Bolei Zhou, Chen Change Loy

SinGAN shows impressive capability in learning internal patch distribution despite its limited effective receptive field. We are interested in knowing how such a translation-invariant convolutional generator could capture the global structure with just a spatially i.i.d. input. In this work, taking SinGAN and StyleGAN2 as examples, we show that such capability, to a large extent, is brought by the implicit positional encoding when using zero padding in the generators. Such positional encoding is indispensable for generating images with high fidelity. The same phenomenon is observed in other generative architectures such as DCGAN and PGGAN. We further show that zero padding leads to an unbalanced spatial bias with a vague relation between locations. To offer a better spatial inductive bias, we investigate alternative positional encodings and analyze their effects. Based on a more flexible positional encoding explicitly, we propose a new multi-scale training strategy and demonstrate its effectiveness in the state-of-the-art unconditional generator StyleGAN2. Besides, the explicit spatial inductive bias substantially improve SinGAN for more versatile image manipulation.

📄 PDF Abstract BibTeX arXiv:2012.05217

Code (0)

등록된 구현이 없습니다.

Tasks

Image ManipulationInductive BiasTranslation

Methods 이 논문이 사용한 방법론

R1 Regularization R_INLINE_MATH_1 Regularization is a regularization technique and gradient penalty for training [generative adversarial…
Path Length Regularization 설명 없음
Weight Demodulation 설명 없음
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Batch Normalization 설명 없음
HuMan(Expedia)||How do I get a human at Expedia? How do I get a human at Expedia? How Do I Get a Human at Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Real-Time Help & Exclusive…
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
StyleGAN2 StyleGAN2 is a generative adversarial network that builds on StyleGAN with several improvements. First, [adaptive instance…

Similar Papers 제목 키워드 기반

Positional Encoding Field

2025-10-23 · Yunpeng Bai, Haoxiang Li, Qixing Huang arxiv

Diffusion Transformers (DiTs) have emerged as the dominant architecture for visual generation, powering state-of-the-art image and video models. By representing images as patch tokens with positional encodings (PEs), DiT…

Novel View SynthesisImage Editing

2-D SSM: A General Spatial Layer for Visual Transformers

2023-06-11 · Ethan Baron, Itamar Zimerman, Lior Wolf

A central objective in computer vision is to design models with appropriate 2-D inductive bias. Desiderata for 2D inductive bias include two-dimensional position awareness, dynamic spatial locality, and translation and p…

Inductive BiasPosition

Investigating Object Compositionality in Generative Adversarial Networks

2018-10-17 · ICLR 2019 5 · Sjoerd van Steenkiste, Karol Kurach, Jürgen Schmidhuber, Sylvain Gelly

Deep generative models seek to recover the process with which the observed data was generated. They may be used to synthesize new samples or to subsequently extract representations. Successful approaches in the domain of…

Image GenerationInductive BiasInstance SegmentationObject+3

Graph Inductive Biases in Transformers without Message Passing

2023-05-27 · Liheng Ma, Chen Lin, Derek Lim, Adriana Romero-Soriano 외

Transformers for graph data are increasingly widely studied and successful in numerous learning tasks. Graph inductive biases are crucial for Graph Transformers, and previous works incorporate them using message-passing …

Graph ClassificationGraph RegressionInductive BiasNode Classification

Toward Spatially Unbiased Generative Models

2021-08-03 · ICCV 2021 10 · Jooyoung Choi, Jungbeom Lee, Yonghyun Jeong, Sungroh Yoon

Recent image generation models show remarkable generation performance. However, they mirror strong location preference in datasets, which we call spatial bias. Therefore, generators render poor samples at unseen location…

DenoisingImage GenerationTranslation