A recipe for watermarking diffusion models
Diffusion models (DMs) have demonstrated advantageous potential on generative tasks.
Widespread interest exists in incorporating DMs into downstream applications, such as …
Widespread interest exists in incorporating DMs into downstream applications, such as …
Task-specific fine-tuning via variational information bottleneck for weakly-supervised pathology whole slide image classification
Abstract While Multiple Instance Learning (MIL) has shown promising results in digital
Pathology Whole Slide Image (WSI) analysis, such a paradigm still faces performance and …
Pathology Whole Slide Image (WSI) analysis, such a paradigm still faces performance and …
Re-thinking model inversion attacks against deep neural networks
Abstract Model inversion (MI) attacks aim to infer and reconstruct private training data by
abusing access to a model. MI attacks have raised concerns about the leaking of sensitive …
abusing access to a model. MI attacks have raised concerns about the leaking of sensitive …
Image synthesis under limited data: A survey and taxonomy
Deep generative models, which target reproducing the data distribution to produce novel
images, have made unprecedented advancements in recent years. However, one critical …
images, have made unprecedented advancements in recent years. However, one critical …
Exploring incompatible knowledge transfer in few-shot image generation
Few-shot image generation (FSIG) learns to generate diverse and high-fidelity images from
a target domain using a few (eg, 10) reference samples. Existing FSIG methods select …
a target domain using a few (eg, 10) reference samples. Existing FSIG methods select …
Label-only model inversion attacks via knowledge transfer
In a model inversion (MI) attack, an adversary abuses access to a machine learning (ML)
model to infer and reconstruct private training data. Remarkable progress has been made in …
model to infer and reconstruct private training data. Remarkable progress has been made in …
Dss-net: Dynamic self-supervised network for video anomaly detection
Video Anomaly detection, aiming to detect the abnormal behaviors in surveillance videos, is
a challenging task since the anomalous events are diversified and complicated in different …
a challenging task since the anomalous events are diversified and complicated in different …
A survey on generative modeling with limited data, few shots, and zero shot
In machine learning, generative modeling aims to learn to generate new data statistically
similar to the training data distribution. In this paper, we survey learning generative models …
similar to the training data distribution. In this paper, we survey learning generative models …
Lfs-gan: Lifelong few-shot image generation
We address a challenging lifelong few-shot image generation task for the first time. In this
situation, a generative model learns a sequence of tasks using only a few samples per task …
situation, a generative model learns a sequence of tasks using only a few samples per task …
Domain re-modulation for few-shot generative domain adaptation
In this study, we delve into the task of few-shot Generative Domain Adaptation (GDA), which
involves transferring a pre-trained generator from one domain to a new domain using only a …
involves transferring a pre-trained generator from one domain to a new domain using only a …