Fast sampling of diffusion models via operator learning
Diffusion models have found widespread adoption in various areas. However, their
sampling process is slow because it requires hundreds to thousands of network evaluations …
sampling process is slow because it requires hundreds to thousands of network evaluations …
Wavefake: A data set to facilitate audio deepfake detection
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 …
Recognizing this threat, a magnitude of research into detecting so-called" Deepfakes" has …
Beam enumeration: probabilistic explainability for sample efficient self-conditioned molecular design
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 …
marked by the surge in very recent papers reporting experimental validation. Key challenges …
Dasco: Dual-generator adversarial support constrained offline reinforcement learning
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 …
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
Explicit visible videos can provide sufficient visual information and facilitate vision
applications. Unfortunately, the image sensors of visible cameras are sensitive to light …
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
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 …
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 …
growing need for high-fidelity, medical image training data. Such data is often scarce due to …
Attribute Based Interpretable Evaluation Metrics for Generative Models
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 …
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 …
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 …
regression or classification tasks on various kinds of data. Other astonishing results have …