Search Results for author:
Found 13 papers, 4 papers with code
Detection Selection Algorithm: A Likelihood based Optimization Method to Perform Post Processing for Object Detection
Third, we propose a whole reconstruction algorithm which generates the joint reconstruction of all objects in a hypothesized interpretation, taking into account occlusion ordering.
Biologically Plausible Training Mechanisms for Self-Supervised Learning in Deep Networks
We develop biologically plausible training mechanisms for self-supervised learning (SSL) in deep networks.
Do We Really Need to Learn Representations from In-domain Data for Outlier Detection?
Unsupervised outlier detection, which predicts if a test sample is an outlier or not using only the information from unlabelled inlier data, is an important but challenging task.
EBMs Trained with Maximum Likelihood are Generator Models Trained with a Self-adverserial Loss
Doing so allows us to study the density induced by the dynamics (if the dynamics are invertible), and connect with GANs by treating the dynamics as generator models, the initial values as latent variables and the loss as optimizing a critic defined by the very same energy that determines the generator through its gradient.
Exponential Tilting of Generative Models: Improving Sample Quality by Training and Sampling from Latent Energy
In this paper, we present a general method that can improve the sample quality of pre-trained likelihood based generative models.
Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encoder
An important application of generative modeling should be the ability to detect out-of-distribution (OOD) samples by setting a threshold on the likelihood.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
A Method to Model Conditional Distributions with Normalizing Flows
In particular, we use our proposed method to analyze inverse problems with invertible neural networks by maximizing the posterior likelihood.
Generative Latent Flow
In this work, we propose the Generative Latent Flow (GLF), an algorithm for generative modeling of the data distribution.
Ranked #1 on
Image Generation
on Fashion-MNIST
Deep learning with asymmetric connections and Hebbian updates
We show that similar performance is achieved with untied layers, also known as locally connected layers, corresponding to the connectivity implied by the convolutional layers, but where weights are untied and updated separately.
Deformable Classifiers
In this paper, we design a framework for training deformable classifiers, where latent transformation variables are introduced, and a transformation of the object image to a reference instantiation is computed in terms of the classifier output, separately for each class.
Dynamic Partition Models
We present a new approach for learning compact and intuitive distributed representations with binary encoding.
Mixtures of Sparse Autoregressive Networks
We consider high-dimensional distribution estimation through autoregressive networks.
Compact Compositional Models
Learning compact and interpretable representations is a very natural task, which has not been solved satisfactorily even for simple binary datasets.
