Fast sampling of diffusion models via operator learning

H Zheng, W Nie, A Vahdat… - International …, 2023 - proceedings.mlr.press
Diffusion models have found widespread adoption in various areas. However, their
sampling process is slow because it requires hundreds to thousands of network evaluations …

Wavefake: A data set to facilitate audio deepfake detection

J Frank, L Schönherr - arxiv preprint arxiv:2111.02813, 2021 - arxiv.org
Deep generative modeling has the potential to cause significant harm to society.
Recognizing this threat, a magnitude of research into detecting so-called" Deepfakes" has …

Beam enumeration: probabilistic explainability for sample efficient self-conditioned molecular design

J Guo, P Schwaller - arxiv preprint arxiv:2309.13957, 2023 - arxiv.org
Generative molecular design has moved from proof-of-concept to real-world applicability, as
marked by the surge in very recent papers reporting experimental validation. Key challenges …

Dasco: Dual-generator adversarial support constrained offline reinforcement learning

Q Vuong, A Kumar, S Levine… - Advances in Neural …, 2022 - proceedings.neurips.cc
In offline RL, constraining the learned policy to remain close to the data is essential to
prevent the policy from outputting out-of-distribution (OOD) actions with erroneously …

On the difficulty of unpaired infrared-to-visible video translation: Fine-grained content-rich patches transfer

Z Yu, S Li, Y Shen, CH Liu… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Explicit visible videos can provide sufficient visual information and facilitate vision
applications. Unfortunately, the image sensors of visible cameras are sensitive to light …

[HTML][HTML] Consistency regularisation in varying contexts and feature perturbations for semi-supervised semantic segmentation of histology images

RMS Bashir, T Qaiser, SEA Raza, NM Rajpoot - Medical Image Analysis, 2024 - Elsevier
Semantic segmentation of various tissue and nuclei types in histology images is
fundamental to many downstream tasks in the area of computational pathology (CPath). In …

Medical Imaging Complexity and its Effects on GAN Performance

W Cagas, C Ko, B Hsiao, S Grandhi… - Proceedings of the …, 2024 - openaccess.thecvf.com
The proliferation of machine learning models in diverse clinical applications has led to a
growing need for high-fidelity, medical image training data. Such data is often scarce due to …

Attribute Based Interpretable Evaluation Metrics for Generative Models

D Kim, M Kwon, Y Uh - arxiv preprint arxiv:2310.17261, 2023 - arxiv.org
When the training dataset comprises a 1: 1 proportion of dogs to cats, a generative model
that produces 1: 1 dogs and cats better resembles the training species distribution than …

SAGAN: Skip attention generative adversarial networks for few-shot image generation

A Aldhubri, J Lu, G Fu - Digital Signal Processing, 2024 - Elsevier
The task of producing high-quality, realistic, and diverse images based on a few instances of
newly emerging or long-tail categories is known as few-shot image generation. Despite prior …

Unpaired high-resolution and scalable style transfer using generative adversarial networks

A Junginger, M Hanselmann, T Strauss… - arxiv preprint arxiv …, 2018 - arxiv.org
Neural networks have proven their capabilities by outperforming many other approaches on
regression or classification tasks on various kinds of data. Other astonishing results have …