Non-maximum Suppression Also Closes the Variational Approximation Gap of Multi-object Variational Autoencoders
Learning object-centric scene representations is crucial for scene structural understanding. However, current unsupervised scene factorization and representation learning models do not reason about scene objects' relations while making an inference. In this paper, we address the issue by introducing a differentiable correlation prior that forces the inference models to suppress duplicate object representations. The extension is evaluated by adding it to three different scene understanding approaches. The results show that the models trained with the proposed method not only outperform the original models in scene factorization and have fewer duplicate representations, but also close the approximation gap between the data evidence and the evidence lower bound.
Code (0)
등록된 구현이 없습니다.
Tasks
ObjectRepresentation LearningScene UnderstandingSimilar Papers 제목 키워드 기반
$k$-means as a variational EM approximation of Gaussian mixture models
We show that $k$-means (Lloyd's algorithm) is obtained as a special case when truncated variational EM approximations are applied to Gaussian Mixture Models (GMM) with isotropic Gaussians. In contrast to the standard way…
ClusteringKnown Unknowns: Uncertainty Quality in Bayesian Neural Networks
We evaluate the uncertainty quality in neural networks using anomaly detection. We extract uncertainty measures (e.g. entropy) from the predictions of candidate models, use those measures as features for an anomaly detec…
Anomaly DetectionKnown UnknownsVariational Prediction
Bayesian inference offers benefits over maximum likelihood, but it also comes with computational costs. Computing the posterior is typically intractable, as is marginalizing that posterior to form the posterior predictiv…
Bayesian InferencePredictionBoosting Variational Inference
Variational inference (VI) provides fast approximations of a Bayesian posterior in part because it formulates posterior approximation as an optimization problem: to find the closest distribution to the exact posterior ov…
Variational InferenceMaximizing submodular functions using probabilistic graphical models
We consider the problem of maximizing submodular functions; while this problem is known to be NP-hard, several numerically efficient local search techniques with approximation guarantees are available. In this paper, we …
Variational Inference