paper-with-me

Papers

Unsupervised Representation Learning with Laplacian Pyramid Auto-encoders

2018-01-16 · Qilu Zhao, Zongmin Li

Scale-space representation has been popular in computer vision community due to its theoretical foundation. The motivation for generating a scale-space representation of a given data set originates from the basic observation that real-world objects are composed of different structures at different scales. Hence, it's reasonable to consider learning features with image pyramids generated by smoothing and down-sampling operations. In this paper we propose Laplacian pyramid auto-encoders, a straightforward modification of the deep convolutional auto-encoder architecture, for unsupervised representation learning. The method uses multiple encoding-decoding sub-networks within a Laplacian pyramid framework to reconstruct the original image and the low pass filtered images. The last layer of each encoding sub-network also connects to an encoding layer of the sub-network in the next level, which aims to reverse the process of Laplacian pyramid generation. Experimental results showed that Laplacian pyramid benefited the classification and reconstruction performance of deep auto-encoder approaches, and batch normalization is critical to get deep auto-encoders approaches to begin learning.

📄 PDF Abstract BibTeX arXiv:1801.05278

Code (0)

등록된 구현이 없습니다.

Tasks

Representation Learning

Methods 이 논문이 사용한 방법론

Batch Normalization 설명 없음

Similar Papers 제목 키워드 기반

Scale-Space Autoencoders for Unsupervised Anomaly Segmentation in Brain MRI

2020-06-23 · Christoph Baur, Benedikt Wiestler, Shadi Albarqouni, Nassir Navab

Brain pathologies can vary greatly in size and shape, ranging from few pixels (i.e. MS lesions) to large, space-occupying tumors. Recently proposed Autoencoder-based methods for unsupervised anomaly segmentation in brain…

Anomaly Segmentation

Laplacian Autoencoders for Learning Stochastic Representations

2022-06-30 · Marco Miani, Frederik Warburg, Pablo Moreno-Muñoz, Nicke Skafte Detlefsen 외

Established methods for unsupervised representation learning such as variational autoencoders produce none or poorly calibrated uncertainty estimates making it difficult to evaluate if learned representations are stable …

Bayesian InferenceOut-of-Distribution DetectionRepresentation Learning

Symmetric Graph Convolutional Autoencoder for Unsupervised Graph Representation Learning

2019-08-07 · ICCV 2019 10 · Jiwoong Park, Minsik Lee, Hyung Jin Chang, Kyuewang Lee 외

We propose a symmetric graph convolutional autoencoder which produces a low-dimensional latent representation from a graph. In contrast to the existing graph autoencoders with asymmetric decoder parts, the proposed autoe…

ClusteringDecoderGraph ClusteringGraph Representation Learning+3

Laplacian Denoising Autoencoder

2020-03-30 · Jianbo Jiao, Linchao Bao, Yunchao Wei, Shengfeng He 외

While deep neural networks have been shown to perform remarkably well in many machine learning tasks, labeling a large amount of ground truth data for supervised training is usually very costly to scale. Therefore, learn…

DenoisingSelf-Supervised Learning

Perceptually Optimized Deep High-Dynamic-Range Image Tone Mapping

2021-09-01 · Chenyang Le, Jiebin Yan, Yuming Fang, Kede Ma

We describe a deep high-dynamic-range (HDR) image tone mapping operator that is computationally efficient and perceptually optimized. We first decompose an HDR image into a normalized Laplacian pyramid, and use two deep …

Tone MappingVocal Bursts Intensity Prediction