Deep Variational Inference Without Pixel-Wise Reconstruction
Variational autoencoders (VAEs), that are built upon deep neural networks have emerged as popular generative models in computer vision. Most of the work towards improving variational autoencoders has focused mainly on making the approximations to the posterior flexible and accurate, leading to tremendous progress. However, there have been limited efforts to replace pixel-wise reconstruction, which have known shortcomings. In this work, we use real-valued non-volume preserving transformations (real NVP) to exactly compute the conditional likelihood of the data given the latent distribution. We show that a simple VAE with this form of reconstruction is competitive with complicated VAE structures, on image modeling tasks. As part of our model, we develop powerful conditional coupling layers that enable real NVP to learn with fewer intermediate layers.
Code (0)
등록된 구현이 없습니다.
Tasks
Variational InferenceMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
A Case for the Score: Identifying Image Anomalies using Variational Autoencoder Gradients
Through training on unlabeled data, anomaly detection has the potential to impact computer-aided diagnosis by outlining suspicious regions. Previous work on deep-learning-based anomaly detection has primarily focused on …
Anomaly DetectionPixelwise Uncertainty Quantification of Accelerated MRI Reconstruction
Parallel imaging techniques reduce magnetic resonance imaging (MRI) scan time but image quality degrades as the acceleration factor increases. In clinical practice, conservative acceleration factors are chosen because no…
Image ReconstructionMRI ReconstructionContext-encoding Variational Autoencoder for Unsupervised Anomaly Detection
Unsupervised learning can leverage large-scale data sources without the need for annotations. In this context, deep learning-based auto encoders have shown great potential in detecting anomalies in medical images. Howeve…
Anomaly DetectionUnsupervised Anomaly DetectionAnomaly detection through latent space restoration using vector-quantized variational autoencoders
We propose an out-of-distribution detection method that combines density and restoration-based approaches using Vector-Quantized Variational Auto-Encoders (VQ-VAEs). The VQ-VAE model learns to encode images in a categori…
Anomaly DetectionOut-of-Distribution DetectionUnsupervised Anomaly DetectionBayesian Uncertainty Estimation of Learned Variational MRI Reconstruction
Recent deep learning approaches focus on improving quantitative scores of dedicated benchmarks, and therefore only reduce the observation-related (aleatoric) uncertainty. However, the model-immanent (epistemic) uncertain…
MRI Reconstruction