Search Results for author:
Found 3 papers, 2 papers with code
SSL-WM: A Black-Box Watermarking Approach for Encoders Pre-trained by Self-supervised Learning
Recent years have witnessed tremendous success in Self-Supervised Learning (SSL), which has been widely utilized to facilitate various downstream tasks in Computer Vision (CV) and Natural Language Processing (NLP) domains.
CTRL: Clustering Training Losses for Label Error Detection
We propose a novel framework, called CTRL (Clustering TRaining Losses for label error detection), to detect label errors in multi-class datasets.
Invisible Backdoor Attacks Using Data Poisoning in the Frequency Domain
However, most of the triggers used in the current study are fixed patterns patched on a small fraction of an image and are often clearly mislabeled, which is easily detected by humans or defense methods such as Neural Cleanse and SentiNet.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
