Towards out-of-distribution generalization: A survey
Traditional machine learning paradigms are based on the assumption that both training and
test data follow the same statistical pattern, which is mathematically referred to as …
test data follow the same statistical pattern, which is mathematically referred to as …
Diffusion model as representation learner
Abstract Diffusion Probabilistic Models (DPMs) have recently demonstrated impressive
results on various generative tasks. Despite its promises, the learned representations of pre …
results on various generative tasks. Despite its promises, the learned representations of pre …
Priority-centric human motion generation in discrete latent space
Text-to-motion generation is a formidable task, aiming to produce human motions that align
with the input text while also adhering to human capabilities and physical laws. While there …
with the input text while also adhering to human capabilities and physical laws. While there …
GDA: Generalized Diffusion for Robust Test-time Adaptation
Abstract Machine learning models face generalization challenges when exposed to out-of-
distribution (OOD) samples with unforeseen distribution shifts. Recent research reveals that …
distribution (OOD) samples with unforeseen distribution shifts. Recent research reveals that …
Generator born from classifier
In this paper, we make a bold attempt toward an ambitious task: given a pre-trained
classifier, we aim to reconstruct an image generator, without relying on any data samples …
classifier, we aim to reconstruct an image generator, without relying on any data samples …
Unveil conditional diffusion models with classifier-free guidance: A sharp statistical theory
Conditional diffusion models serve as the foundation of modern image synthesis and find
extensive application in fields like computational biology and reinforcement learning. In …
extensive application in fields like computational biology and reinforcement learning. In …
Dispel: Domain generalization via domain-specific liberating
Domain generalization aims to learn a generalization model that can perform well on
unseen test domains by only training on limited source domains. However, existing domain …
unseen test domains by only training on limited source domains. However, existing domain …
Tackling Structural Hallucination in Image Translation with Local Diffusion
Recent developments in diffusion models have advanced conditioned image generation, yet
they struggle with reconstructing out-of-distribution (OOD) images, such as unseen tumors in …
they struggle with reconstructing out-of-distribution (OOD) images, such as unseen tumors in …
[HTML][HTML] Investigation of out-of-distribution detection across various models and training methodologies
BC Kim, B Kim, Y Hyun - Neural Networks, 2024 - Elsevier
Abstract Machine learning-based algorithms demonstrate impressive performance across
numerous fields; however, they continue to suffer from certain limitations. Even sophisticated …
numerous fields; however, they continue to suffer from certain limitations. Even sophisticated …
Diagnosing and Rectifying Fake OOD Invariance: A Restructured Causal Approach
Invariant representation learning (IRL) encourages the prediction from invariant causal
features to labels deconfounded from the environments, advancing the technical roadmap of …
features to labels deconfounded from the environments, advancing the technical roadmap of …