2 papers
cs.CV2024
Joint-Embedding Predictive Architecture for Self-Supervised Learning of Mask Classification Architecture
Dong-Hee Kim, Sungduk Cho, Hyeonwoo Cho +3
In this work, we introduce Mask-JEPA, a self-supervised learning framework tailored for mask classification architectures (MCA), to overcome the traditional constraints associated…
cs.LG2024
Learning to Approximate Adaptive Kernel Convolution on Graphs
Jaeyoon Sim, Sooyeon Jeon, InJun Choi +2
Various Graph Neural Networks (GNNs) have been successful in analyzing data in non-Euclidean spaces, however, they have limitations such as oversmoothing, i.e., information becomes…