2 papers
cs.CV2025
Stable-Drift: A Patient-Aware Latent Drift Replay Method for Stabilizing Representations in Continual Learning
Paraskevi-Antonia Theofilou, Anuhya Thota, Stefanos Kollias +1
When deep learning models are sequentially trained on new data, they tend to abruptly lose performance on previously learned tasks, a critical failure known as catastrophic forgett…
cs.CV2025
EquiCaps: Predictor-Free Pose-Aware Pre-Trained Capsule Networks
Athinoulla Konstantinou, Georgios Leontidis, Mamatha Thota +1
Learning self-supervised representations that are invariant and equivariant to transformations is crucial for advancing beyond traditional visual classification tasks. However, man…