Search Results for author:
Found 8 papers, 3 papers with code
Generalized Contrastive Divergence: Joint Training of Energy-Based Model and Diffusion Model through Inverse Reinforcement Learning
We present Generalized Contrastive Divergence (GCD), a novel objective function for training an energy-based model (EBM) and a sampler simultaneously.
Evaluating Out-of-Distribution Detectors Through Adversarial Generation of Outliers
A reliable evaluation method is essential for building a robust out-of-distribution (OOD) detector.
Regularized Autoencoders for Isometric Representation Learning
The recent success of autoencoders for representation learning can be traced in large part to the addition of a regularization term.
Adversarial Distributions Against Out-of-Distribution Detectors
As an outlier may deviate from the training distribution in unexpected ways, an ideal OOD detector should be able to detect all types of outliers.
Autoencoding Under Normalization Constraints
The specific role of the normalization constraint is to ensure that the out-of-distribution (OOD) regime has a small likelihood when samples are learned using maximum likelihood.
Spectrally Similar Graph Pooling
To further investigate the effectiveness of our proposed method, we evaluate our approach on a real-world problem, image retrieval with visual scene graphs.
Suppressing Outlier Reconstruction in Autoencoders for Out-of-Distribution Detection
This phenomenon, which we refer to as outlier reconstruction, has a detrimental effect on the use of autoencoders for outlier detection, as an autoencoder will misclassify a clear outlier as being in-distribution.
Image-to-Image Retrieval by Learning Similarity between Scene Graphs
Based on this idea, we propose a novel approach for image-to-image retrieval using scene graph similarity measured by graph neural networks.
