English
Related papers

Related papers: Local-Order Auxiliary Losses Can Improve Autoencod…

200 papers

We study sparse signal recovery from noisy linear observations using nonconvex log-sum regularization. The log-sum penalty reduces the shrinkage bias of $\ell_1$ regularization and more closely approximates the $\ell_0$ regularization, but…

Information Theory · Computer Science 2026-05-12 Keisuke Morita , Masayuki Ohzeki

The loss functions of deep neural networks are complex and their geometric properties are not well understood. We show that the optima of these complex loss functions are in fact connected by simple curves over which training and test…

Machine Learning · Statistics 2018-10-31 Timur Garipov , Pavel Izmailov , Dmitrii Podoprikhin , Dmitry Vetrov , Andrew Gordon Wilson

We propose a deep learning approach based on an autoencoder for identifying and localizing fiber faults in passive optical networks. The experimental results show that the proposed method detects faults with 97% accuracy, pinpoints them…

Signal Processing · Electrical Eng. & Systems 2022-03-23 Khouloud Abdelli , Florian Azendorf , Helmut Griesser , Carsten Tropschug , Stephan Pachnicke

Federated learning (FL), as a collaborative distributed training paradigm with several edge computing devices under the coordination of a centralized server, is plagued by inconsistent local stationary points due to the heterogeneity of the…

Systems and Control · Electrical Eng. & Systems 2023-02-14 Yixing Liu , Yan Sun , Zhengtao Ding , Li Shen , Bo Liu , Dacheng Tao

Linear autoencoder models learn an item-to-item weight matrix via convex optimization with L2 regularization and zero-diagonal constraints. Despite their simplicity, they have shown remarkable performance compared to sophisticated…

Information Retrieval · Computer Science 2023-05-23 Jaewan Moon , Hye-young Kim , Jongwuk Lee

Sparse autoencoders (SAEs) are a technique for sparse decomposition of neural network activations into human-interpretable features. However, current SAEs suffer from feature absorption, where specialized features capture instances of…

Machine Learning · Computer Science 2025-09-29 Anton Korznikov , Andrey Galichin , Alexey Dontsov , Oleg Rogov , Elena Tutubalina , Ivan Oseledets

Cross-Domain Few-Shot Learning (CDFSL) requires the model to transfer knowledge from the data-abundant source domain to data-scarce target domains for fast adaptation, where the large domain gap makes CDFSL a challenging problem. Masked…

Computer Vision and Pattern Recognition · Computer Science 2024-12-30 Ran Ma , Yixiong Zou , Yuhua Li , Ruixuan Li

Sparse autoencoders (SAEs) have been widely used for interpretability of neural networks, but their learned features often vary across seeds and hyperparameter settings. We introduce Ordered Sparse Autoencoders (OSAE), which extend…

Machine Learning · Computer Science 2025-12-03 Sophie L. Wang , Alex Quach , Nithin Parsan , John J. Yang

This paper presents a learning method for convolutional autoencoders (CAEs) for extracting features from images. CAEs can be obtained by utilizing convolutional neural networks to learn an approximation to the identity function in an…

Computer Vision and Pattern Recognition · Computer Science 2018-06-27 Naoyuki Ichimura

We consider estimating a random vector from its noisy projections onto low dimensional subspaces constituting a fusion frame. A fusion frame is a collection of subspaces, for which the sum of the projection operators onto the subspaces is…

Functional Analysis · Mathematics 2007-09-17 Gitta Kutyniok , Ali Pezeshki , Robert Calderbank , Taotao Liu

Autoencoders are certainly among the most studied and used Deep Learning models: the idea behind them is to train a model in order to reconstruct the same input data. The peculiarity of these models is to compress the information through a…

Machine Learning · Computer Science 2023-09-06 Gabriele Martino , Davide Moroni , Massimo Martinelli

We consider the problem of estimating an unknown signal $x_0$ from noisy linear observations $y = Ax_0 + z\in R^m$. In many practical instances, $x_0$ has a certain structure that can be captured by a structure inducing convex function…

Information Theory · Computer Science 2013-11-07 Samet Oymak , Christos Thrampoulidis , Babak Hassibi

Autoencoders have achieved great success in various computer vision applications. The autoencoder learns appropriate low dimensional image representations through the self-supervised paradigm, i.e., reconstruction. Existing studies mainly…

Computer Vision and Pattern Recognition · Computer Science 2023-04-18 Jianzhang Zheng , Hao Shen , Jian Yang , Xuan Tang , Mingsong Chen , Hui Yu , Jielong Guo , Xian Wei

We consider a wireless sensor network, sampling a bandlimited field, described by a limited number of harmonics. Sensor nodes are irregularly deployed over the area of interest or subject to random motion; in addition sensors measurements…

Other Computer Science · Computer Science 2009-11-13 A. Nordio , C. -F. Chiasserini , E. Viterbo

It has been shown, that high resolution images can be acquired using a low resolution sensor with non-regular sampling. Therefore, post-processing is necessary. In terms of video data, not only the spatial neighborhood can be used to assist…

Image and Video Processing · Electrical Eng. & Systems 2022-09-29 Andreas Spruck , Markus Jonscher , JÜrgen Seiler , André Kaup

This research presents a novel depth estimation algorithm based on a Transformer-encoder architecture, tailored for the NYU and KITTI Depth Dataset. This research adopts a transformer model, initially renowned for its success in natural…

Computer Vision and Pattern Recognition · Computer Science 2024-06-25 Linhan Xia , Junbang Liu , Tong Wu

Autoencoders, which consist of an encoder and a decoder, are widely used in machine learning for dimension reduction of high-dimensional data. The encoder embeds the input data manifold into a lower-dimensional latent space, while the…

Numerical Analysis · Mathematics 2024-03-29 Juliane Braunsmann , Marko Rajković , Martin Rumpf , Benedikt Wirth

Emerging interests have been brought to recognize previously unseen objects given very few training examples, known as few-shot object detection (FSOD). Recent researches demonstrate that good feature embedding is the key to reach favorable…

Computer Vision and Pattern Recognition · Computer Science 2021-03-16 Bo Sun , Banghuai Li , Shengcai Cai , Ye Yuan , Chi Zhang

The purpose of signal extrapolation is to estimate unknown signal parts from known samples. This task is especially important for error concealment in image and video communication. For obtaining a high quality reconstruction, assumptions…

Computer Vision and Pattern Recognition · Computer Science 2022-05-17 Ján Koloda , Jürgen Seiler , André Kaup , Victoria Sánchez , Antonio M. Peinado

This paper studies selecting a subset of the system's output to minimize the state estimation mean square error (MSE). This results in the maximization problem of a set function defined on possible sensor selections subject to a cardinality…

Systems and Control · Electrical Eng. & Systems 2020-09-29 Akira Kohara , Kunihisa Okano , Kentaro Hirata , Yukinori Nakamura