Search Results for author:
Found 10 papers, 4 papers with code
HFI: A unified framework for training-free detection and implicit watermarking of latent diffusion model generated images
Specifically, by viewing the autoencoder of LDM as a downsampling-upsampling kernel, HFI measures the extent of aliasing, a distortion of high-frequency information that appears in the reconstructed image.
Diffusion based Semantic Outlier Generation via Nuisance Awareness for Out-of-Distribution Detection
Out-of-distribution (OOD) detection, which determines whether a given sample is part of the in-distribution (ID), has recently shown promising results through training with synthetic OOD datasets.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Partial-Multivariate Model for Forecasting
When solving forecasting problems including multiple time-series features, existing approaches often fall into two extreme categories, depending on whether to utilize inter-feature information: univariate and complete-multivariate models.
Learning Equi-angular Representations for Online Continual Learning
Online continual learning suffers from an underfitted solution due to insufficient training for prompt model update (e. g., single-epoch training).
Projection Regret: Reducing Background Bias for Novelty Detection via Diffusion Models
Based on our observation that diffusion models can \emph{project} any sample to an in-distribution sample with similar background information, we propose \emph{Projection Regret (PR)}, an efficient novelty detection method that mitigates the bias of non-semantic information.
Observation-Guided Diffusion Probabilistic Models
We propose a novel diffusion-based image generation method called the observation-guided diffusion probabilistic model (OGDM), which effectively addresses the tradeoff between quality control and fast sampling.
Transferring Pre-trained Multimodal Representations with Cross-modal Similarity Matching
Despite surprising performance on zero-shot transfer, pre-training a large-scale multimodal model is often prohibitive as it requires a huge amount of data and computing resources.
Unsupervised Visual Representation Learning via Mutual Information Regularized Assignment
This paper proposes Mutual Information Regularized Assignment (MIRA), a pseudo-labeling algorithm for unsupervised representation learning inspired by information maximization.
Novelty Detection Via Blurring
Conventional out-of-distribution (OOD) detection schemes based on variational autoencoder or Random Network Distillation (RND) have been observed to assign lower uncertainty to the OOD than the target distribution.
Sample-Efficient Deep Reinforcement Learning via Episodic Backward Update
We propose Episodic Backward Update (EBU) - a novel deep reinforcement learning algorithm with a direct value propagation.
