English
Related papers

Related papers: Winner-Take-All Autoencoders

200 papers

Variational autoencoders (VAEs) are widely used deep generative models capable of learning unsupervised latent representations of data. Such representations are often difficult to interpret or control. We consider the problem of…

Machine Learning · Computer Science 2018-12-18 Jack Klys , Jake Snell , Richard Zemel

When sensors collect spatio-temporal data in a large geographical area, the existence of missing data cannot be escaped. Missing data negatively impacts the performance of data analysis and machine learning algorithms. In this paper, we…

Machine Learning · Computer Science 2019-04-30 Reza Asadi , Amelia Regan

Fine-tuning pre-trained transformers is a powerful technique for enhancing the performance of base models on specific tasks. From early applications in models like BERT to fine-tuning Large Language Models (LLMs), this approach has been…

Computation and Language · Computer Science 2025-02-25 Suneel Nadipalli

The concept of sparsity has been extensively applied for regularization in image reconstruction. Typically, sparsifying transforms are either pre-trained on ground-truth images or adaptively trained during the reconstruction. Thereby,…

Image and Video Processing · Electrical Eng. & Systems 2022-03-07 Andreas Kofler , Christian Wald , Tobias Schaeffter , Markus Haltmeier , Christoph Kolbitsch

Understanding the internal representations of large language models is crucial for ensuring their reliability and safety, with sparse autoencoders (SAEs) emerging as a promising interpretability approach. However, current SAE training…

Machine Learning · Computer Science 2025-10-13 T. Ed Li , Junyu Ren

This work studies the problem of modeling visual processes by leveraging deep generative architectures for learning linear, Gaussian representations from observed sequences. We propose a joint learning framework, combining a vector…

Neural and Evolutionary Computing · Computer Science 2020-04-13 Alexander Sagel , Hao Shen

There has been a lot of recent interest in designing neural network models to estimate a distribution from a set of examples. We introduce a simple modification for autoencoder neural networks that yields powerful generative models. Our…

Machine Learning · Computer Science 2015-06-08 Mathieu Germain , Karol Gregor , Iain Murray , Hugo Larochelle

In this paper, we introduce an unsupervised learning approach to automatically discover, summarize, and manipulate artistic styles from large collections of paintings. Our method is based on archetypal analysis, which is an unsupervised…

Machine Learning · Statistics 2018-10-03 Daan Wynen , Cordelia Schmid , Julien Mairal

Learning from limited data is challenging because data scarcity leads to a poor generalization of the trained model. A classical global pooled representation will probably lose useful local information. Many few-shot learning methods have…

Computer Vision and Pattern Recognition · Computer Science 2023-05-11 Haoxing Chen , Huaxiong Li , Yaohui Li , Chunlin Chen

Sparse Autoencoders (SAEs) are increasingly used to interpret foundation models, but their role as an actionable intervention space remains less understood, especially in vision. We study whether sparse visual features can be used not only…

Computer Vision and Pattern Recognition · Computer Science 2026-05-28 Gerasimos Chatzoudis , Zhuowei Li , Gemma E. Moran , Hao Wang , Dimitris N. Metaxas

Continual learning on edge devices poses unique challenges due to stringent resource constraints. This paper introduces a novel method that leverages stochastic competition principles to promote sparsity, significantly reducing deep network…

Machine Learning · Computer Science 2024-07-16 Theodoros Christophides , Kyriakos Tolias , Sotirios Chatzis

Intelligent behaviour in the real-world requires the ability to acquire new knowledge from an ongoing sequence of experiences while preserving and reusing past knowledge. We propose a novel algorithm for unsupervised representation learning…

Generative processes in biology and other fields often produce data that can be regarded as resulting from a composition of basic features. Here we present an unsupervised method based on autoencoders for inferring these basic features of…

Quantitative Methods · Quantitative Biology 2019-10-04 Matteo Negri , Davide Bergamini , Carlo Baldassi , Riccardo Zecchina , Christoph Feinauer

While artificial neural networks excel in unsupervised learning of non-sparse structure, classical statistical regression techniques offer better interpretability, in particular when sparseness is enforced by $\ell_1$ regularization,…

In this paper, we design and evaluate a convolutional autoencoder that perturbs an input face image to impart privacy to a subject. Specifically, the proposed autoencoder transforms an input face image such that the transformed image can be…

Computer Vision and Pattern Recognition · Computer Science 2018-05-04 Vahid Mirjalili , Sebastian Raschka , Anoop Namboodiri , Arun Ross

We propose a lossy image compression system using the deep-learning autoencoder structure to participate in the Challenge on Learned Image Compression (CLIC) 2018. Our autoencoder uses the residual blocks with skip connections to reduce the…

Computer Vision and Pattern Recognition · Computer Science 2019-02-21 David Alexandre , Chih-Peng Chang , Wen-Hsiao Peng , Hsueh-Ming Hang

Ensemble weather predictions typically show systematic errors that have to be corrected via post-processing. Even state-of-the-art post-processing methods based on neural networks often solely rely on location-specific predictors that…

Machine Learning · Computer Science 2022-04-12 Sebastian Lerch , Kai L. Polsterer

Visual representation is crucial for a visual tracking method's performances. Conventionally, visual representations adopted in visual tracking rely on hand-crafted computer vision descriptors. These descriptors were developed generically…

Computer Vision and Pattern Recognition · Computer Science 2016-04-15 Jason Kuen , Kian Ming Lim , Chin Poo Lee

The recently developed variational autoencoders (VAEs) have proved to be an effective confluence of the rich representational power of neural networks with Bayesian methods. However, most work on VAEs use a rather simple prior over the…

Machine Learning · Computer Science 2017-08-29 Prasoon Goyal , Zhiting Hu , Xiaodan Liang , Chenyu Wang , Eric Xing

Auto-encoder models that preserve similarities in the data are a popular tool in representation learning. In this paper we introduce several auto-encoder models that preserve local distances when mapping from the data space to the latent…

Machine Learning · Computer Science 2022-10-03 Nutan Chen , Patrick van der Smagt , Botond Cseke
‹ Prev 1 4 5 6 7 8 10 Next ›