1 citations · 1 across the 4 of their papers we have counts for
4 papers
Point-PNG: Conditional Pseudo-Negatives Generation for Point Cloud Pre-Training
Sutharsan Mahendren, Saimunur Rahman, Piotr Koniusz +4
We propose Point-PNG, a novel self-supervised learning framework that generates conditional pseudo-negatives in the latent space to learn point cloud representations that are both…
Pre-training with Random Orthogonal Projection Image Modeling
Maryam Haghighat, Peyman Moghadam, Shaheer Mohamed +1
Masked Image Modeling (MIM) is a powerful self-supervised strategy for visual pre-training without the use of labels. MIM applies random crops to input images, processes them with…
Multivariate Prototype Representation for Domain-Generalized Incremental Learning
Can Peng, Piotr Koniusz, Kaiyu Guo +2
Deep learning models suffer from catastrophic forgetting when being fine-tuned with samples of new classes. This issue becomes even more pronounced when faced with the domain shift…
Exploiting Field Dependencies for Learning on Categorical Data
Zhibin Li, Piotr Koniusz, Lu Zhang +2
Traditional approaches for learning on categorical data underexploit the dependencies between columns (\aka fields) in a dataset because they rely on the embedding of data points d…