Search Results for author:
Found 5 papers, 2 papers with code
UniFormaly: Towards Task-Agnostic Unified Framework for Visual Anomaly Detection
We introduce Back Patch Masking (BPM) and top k-ratio feature matching to achieve unified anomaly detection.
LEAT: Towards Robust Deepfake Disruption in Real-World Scenarios via Latent Ensemble Attack
However, previous approaches primarily focus on generating distorted outputs based on only predetermined target attributes, leading to a lack of robustness in real-world scenarios where target attributes are unknown.
AVATAR: Adversarial self-superVised domain Adaptation network for TARget domain
This paper presents an unsupervised domain adaptation (UDA) method for predicting unlabeled target domain data, specific to complex UDA tasks where the domain gap is significant.
A Framework for Generalizing Critical Heat Flux Detection Models Using Unsupervised Image-to-Image Translation
To deal with datasets from new domains a model needs to be trained from scratch.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
