English
Related papers

Related papers: Enhancing Neural Autoregressive Distribution Estim…

200 papers

Autoencoder reconstructions are widely used for the task of unsupervised anomaly localization. Indeed, an autoencoder trained on normal data is expected to only be able to reconstruct normal features of the data, allowing the segmentation…

Computer Vision and Pattern Recognition · Computer Science 2020-02-11 David Dehaene , Oriel Frigo , Sébastien Combrexelle , Pierre Eline

MRI reconstruction is an inherently ill-posed inverse problem, since incomplete measurements admit many plausible solutions. This ambiguity becomes more severe under high acceleration, where pixel-domain continuous predictors tend to…

Image and Video Processing · Electrical Eng. & Systems 2026-05-22 Yilmaz Korkmaz , Vishal M. Patel

We present a method for feature interpretation that makes use of recent advances in autoregressive density estimation models to invert model representations. We train generative inversion models to express a distribution over input features…

Machine Learning · Statistics 2019-01-03 Charlie Nash , Nate Kushman , Christopher K. I. Williams

Observing certain patches in an image reduces the uncertainty of others. Their realization lowers the distribution entropy of each remaining patch feature, analogous to collapsing a particle's wave function in quantum mechanics. This…

Computer Vision and Pattern Recognition · Computer Science 2025-12-01 Wei Guo , Shunqi Mao , Zhuonan Liang , Heng Wang , Weidong Cai

In this work, we propose a new unsupervised image segmentation approach based on mutual information maximization between different constructed views of the inputs. Taking inspiration from autoregressive generative models that predict the…

Computer Vision and Pattern Recognition · Computer Science 2020-07-17 Yassine Ouali , Céline Hudelot , Myriam Tami

We present a pixel recursive super resolution model that synthesizes realistic details into images while enhancing their resolution. A low resolution image may correspond to multiple plausible high resolution images, thus modeling the super…

Computer Vision and Pattern Recognition · Computer Science 2017-03-23 Ryan Dahl , Mohammad Norouzi , Jonathon Shlens

Autoregressive models are a class of exact inference approaches with highly flexible functional forms, yielding state-of-the-art density estimates for natural images. Yet, the sequential ordering on the dimensions makes these models…

Computer Vision and Pattern Recognition · Computer Science 2021-10-19 Shweta Mahajan , Stefan Roth

Conditional neural processes (CNPs) are a flexible and efficient family of models that learn to learn a stochastic process from data. They have seen particular application in contextual image completion - observing pixel values at some…

Machine Learning · Computer Science 2024-02-20 Victor Prokhorov , Ivan Titov , N. Siddharth

Encoder-decoder networks have found widespread use in various dense prediction tasks. However, the strong reduction of spatial resolution in the encoder leads to a loss of location information as well as boundary artifacts. To address this,…

Computer Vision and Pattern Recognition · Computer Science 2020-04-01 Anne S. Wannenwetsch , Stefan Roth

Predicting masked from visible parts of an image is a powerful self-supervised approach for visual representation learning. However, the common practice of masking random patches of pixels exhibits certain failure modes, which can prevent…

Machine Learning · Computer Science 2025-02-12 Alice Bizeul , Thomas Sutter , Alain Ryser , Bernhard Schölkopf , Julius von Kügelgen , Julia E. Vogt

Diffusion models have achieved excellent success in solving inverse problems due to their ability to learn strong image priors, but existing approaches require a large training dataset of images that should come from the same distribution…

Computer Vision and Pattern Recognition · Computer Science 2024-10-16 Jason Hu , Bowen Song , Jeffrey A. Fessler , Liyue Shen

Unsupervised dimensionality reduction is one of the commonly used techniques in the field of high dimensional data recognition problems. The deep autoencoder network which constrains the weights to be non-negative, can learn a low…

Computer Vision and Pattern Recognition · Computer Science 2020-09-18 Anyong Qin , Zhaowei Shang , Zhuolin Tan , Taiping Zhang , Yuan Yan Tang

In this paper, we explore a new generative approach for learning visual representations. Our method, DARL, employs a decoder-only Transformer to predict image patches autoregressively. We find that training with Mean Squared Error (MSE)…

Machine Learning · Computer Science 2024-06-05 Yazhe Li , Jorg Bornschein , Ting Chen

Autoregressive neural network models have been used successfully for sequence generation, feature extraction, and hypothesis scoring. This paper presents yet another use for these models: allocating more computation to more difficult…

Machine Learning · Computer Science 2020-06-03 Loren Lugosch , Derek Nowrouzezahrai , Brett H. Meyer

Many unsupervised visual anomaly detection methods train an auto-encoder to reconstruct normal samples and then leverage the reconstruction error map to detect and localize the anomalies. However, due to the powerful modeling and…

Computer Vision and Pattern Recognition · Computer Science 2024-12-18 Qingqing Fang , Qinliang Su , Wenxi Lv , Wenchao Xu , Jianxing Yu

This paper presents a new Expectation Propagation (EP) framework for image restoration using patch-based prior distributions. While Monte Carlo techniques are classically used to sample from intractable posterior distributions, they can…

Computer Vision and Pattern Recognition · Computer Science 2021-11-11 Dan Yao , Stephen McLaughlin , Yoann Altmann

Natural image modeling is a landmark challenge of unsupervised learning. Variational Autoencoders (VAEs) learn a useful latent representation and model global structure well but have difficulty capturing small details. PixelCNN models…

Machine Learning · Computer Science 2016-11-16 Ishaan Gulrajani , Kundan Kumar , Faruk Ahmed , Adrien Ali Taiga , Francesco Visin , David Vazquez , Aaron Courville

Recent neural network models for image captioning usually employ an encoder-decoder architecture, where the decoder adopts a recursive sequence decoding way. However, such autoregressive decoding may result in sequential error accumulation…

Computer Vision and Pattern Recognition · Computer Science 2019-12-16 Zheng-cong Fei

Mitigating bias in machine learning models is a critical endeavor for ensuring fairness and equity. In this paper, we propose a novel approach to address bias by leveraging pixel image attributions to identify and regularize regions of…

Computer Vision and Pattern Recognition · Computer Science 2025-07-08 Sander De Coninck , Sam Leroux , Pieter Simoens

Unsupervised transfer learning-based change detection methods exploit the feature extraction capability of pre-trained networks to distinguish changed pixels from the unchanged ones. However, their performance may vary significantly…

Image and Video Processing · Electrical Eng. & Systems 2024-05-17 Sudipan Saha