English
Related papers

Related papers: Maximum Entropy Auto-Encoding

200 papers

Large occlusions result in a significant decline in image classification accuracy. During inference, diverse types of unseen occlusions introduce out-of-distribution data to the classification model, leading to accuracy dropping as low as…

Computer Vision and Pattern Recognition · Computer Science 2024-02-13 Ketan Kotwal , Tanay Deshmukh , Preeti Gopal

Deep Learning has been widely applied in the area of image processing and natural language processing. In this paper, we propose an end-to-end communication structure based on autoencoder where the transceiver can be optimized jointly. A…

Information Theory · Computer Science 2019-06-18 Tianjie Mu , Xiaohui Chen , Li Chen , Huarui Yin , Weidong Wang

In this paper, we adopt a probability distribution estimation perspective to explore the optimization mechanisms of supervised classification using deep neural networks. We demonstrate that, when employing the Fenchel-Young loss, despite…

Machine Learning · Computer Science 2025-04-01 Binchuan Qi , Wei Gong , Li Li

Deep learning-based methods have revolutionized the field of imaging inverse problems, yielding state-of-the-art performance across various imaging domains. The best performing networks incorporate the imaging operator within the network…

Computer Vision and Pattern Recognition · Computer Science 2026-01-06 Romain Vo , Julián Tachella

We propose to exploit {\em reconstruction} as a layer-local training signal for deep learning. Reconstructions can be propagated in a form of target propagation playing a role similar to back-propagation but helping to reduce the reliance…

Machine Learning · Computer Science 2014-09-19 Yoshua Bengio

In this report, we applied expectation and maximization (EM) method described by Philips et al [1] to recover two-dimensional (2D) structure from multiple sparse signal images in random orientation. The detailed derivation of EM algorithm…

Data Analysis, Statistics and Probability · Physics 2017-01-12 Yun Zhao

We present a principled framework for confidence estimation in computed tomography (CT) reconstruction. Based on the sequential likelihood mixing framework (Kirschner et al., 2025), we establish confidence regions with theoretical coverage…

Machine Learning · Computer Science 2026-02-06 Matteo Gätzner , Johannes Kirschner

Recently, Deep Unfolding Networks (DUNs) have achieved impressive reconstruction quality in the field of image Compressive Sensing (CS) by unfolding iterative optimization algorithms into neural networks. The reconstruction quality of DUNs…

Computer Vision and Pattern Recognition · Computer Science 2025-03-12 Chen Liao , Yan Shen , Dan Li , Zhongli Wang

Data-free compression raises a new challenge because the original training dataset for a pre-trained model to be compressed is not available due to privacy or transmission issues. Thus, a common approach is to compute a reconstructed…

Computer Vision and Pattern Recognition · Computer Science 2021-05-27 Baozhou Zhu , Peter Hofstee , Johan Peltenburg , Jinho Lee , Zaid Alars

Most Deep Learning (DL) based Compressed Sensing (DCS) algorithms adopt a single neural network for signal reconstruction, and fail to jointly consider the influences of the sampling operation for reconstruction. In this paper, we propose…

Computer Vision and Pattern Recognition · Computer Science 2022-11-17 Chunyan Zeng , Jiaxiang Ye , Zhifeng Wang , Nan Zhao , Minghu Wu

Autoencoders are composed of coding and decoding units, hence they hold the inherent potential of high-performance data compression and signal compressed sensing. The main disadvantages of current autoencoders comprise the following several…

Machine Learning · Computer Science 2022-07-28 Honggui Li , Dimitri Galayko , Maria Trocan , Mohamad Sawan

Disentangled distributed representations of data are desirable for machine learning, since they are more expressive and can generalize from fewer examples. However, for complex data, the distributed representations of multiple objects…

Machine Learning · Computer Science 2016-01-21 Klaus Greff , Rupesh Kumar Srivastava , Jürgen Schmidhuber

PET image reconstruction is challenging due to the ill-poseness of the inverse problem and limited number of detected photons. Recently deep neural networks have been widely and successfully used in computer vision tasks and attracted…

Computer Vision and Pattern Recognition · Computer Science 2017-10-11 Kuang Gong , Jiahui Guan , Kyungsang Kim , Xuezhu Zhang , Georges El Fakhri , Jinyi Qi , Quanzheng Li

Deep learning builds deep architectures such as multi-layered artificial neural networks to effectively represent multiple features of input patterns. The adaptive structural learning method of Deep Belief Network (DBN) can realize a high…

Neural and Evolutionary Computing · Computer Science 2019-10-01 Shin Kamada , Takumi Ichimura

We construct a new kind of encoder, leveraging the expressive power of diffusion models. In a traditional variational autoencoder, the encoder and decoder jointly negotiate a latent representation of the input. This is made possible by the…

Machine Learning · Computer Science 2026-05-14 Akhil Premkumar , Sarah Lucioni

We propose a new approach to the problem of optimizing autoencoders for lossy image compression. New media formats, changing hardware technology, as well as diverse requirements and content types create a need for compression algorithms…

Machine Learning · Statistics 2017-03-02 Lucas Theis , Wenzhe Shi , Andrew Cunningham , Ferenc Huszár

Autoencoders learn data representations (codes) in such a way that the input is reproduced at the output of the network. However, it is not always clear what kind of properties of the input data need to be captured by the codes. Kernel…

Machine Learning · Statistics 2018-07-24 Michael Kampffmeyer , Sigurd Løkse , Filippo M. Bianchi , Robert Jenssen , Lorenzo Livi

The leading approach for image compression with artificial neural networks (ANNs) is to learn a nonlinear transform and a fixed entropy model that are optimized for rate-distortion performance. We show that this approach can be…

Computer Vision and Pattern Recognition · Computer Science 2018-06-01 David Minnen , George Toderici , Saurabh Singh , Sung Jin Hwang , Michele Covell

A deep learning approach to blind denoising of images without complete knowledge of the noise statistics is considered. We propose DN-ResNet, which is a deep convolutional neural network (CNN) consisting of several residual blocks…

Image and Video Processing · Electrical Eng. & Systems 2019-04-12 Haoyu Ren , Mostafa El-Khamy , Jungwon Lee

Depth acquisition, based on active illumination, is essential for autonomous and robotic navigation. LiDARs (Light Detection And Ranging) with mechanical, fixed, sampling templates are commonly used in today's autonomous vehicles. An…

Computer Vision and Pattern Recognition · Computer Science 2019-08-06 Adam Wolff , Shachar Praisler , Ilya Tcenov , Guy Gilboa