In practice, users often desire the ability to control object motion and camera movement independently for customized video creation.
I2V-Adapter adeptly propagates the unnoised input image to subsequent noised frames through a cross-frame attention mechanism, maintaining the identity of the input image without any changes to the pretrained T2V model.
To address this, we propose a novel energy-based perspective, enhancing the model's perception of target data distributions without requiring access to training data or processes.
The generalization of neural networks is a central challenge in machine learning, especially concerning the performance under distributions that differ from training ones.
In this paper, we propose and formulate graph adversarial immunization, i. e., vaccinating part of graph structure to improve certifiable robustness of graph against any admissible adversarial attack.
In this paper, we first propose and define camouflage as distribution similarity between ego networks of injected nodes and normal nodes.
Training generative adversarial networks (GANs) with limited data is challenging because the discriminator is prone to overfitting.
Specifically, the proposed auxiliary discriminative classifier becomes generator-aware by recognizing the class-labels of the real data and the generated data discriminatively.
Ranked #1 on Conditional Image Generation on Tiny ImageNet
Recently, transformation-based self-supervised learning has been applied to generative adversarial networks (GANs) to mitigate catastrophic forgetting in the discriminator by introducing a stationary learning environment.
Guided by related sociological theories, we propose a novel Signed Directed Graph Neural Networks model named SDGNN to learn node embeddings for signed directed networks.
In particular, for real-time generation tasks, different devices require generators of different sizes due to varying computing power.
Graph neural networks (GNNs) achieve remarkable success in graph-based semi-supervised node classification, leveraging the information from neighboring nodes to improve the representation learning of target node.
Despite achieving strong performance in semi-supervised node classification task, graph neural networks (GNNs) are vulnerable to adversarial attacks, similar to other deep learning models.
We evaluate the proposed SiGAT method by applying it to the signed link prediction task.
Ranked #1 on Link Sign Prediction on Slashdot