Universal Incremental Learning: Mitigating Confusion from Inter- and Intra-task Distribution Randomness

arXiv:2503.07035 · cs.CV · Submitted 2025-03-10 · Read on arXiv

cs.CV

Submitted: 2025-03-10

Updated: 2026-10-13

Comments: Accepted to Pattern Recognition

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Universal Incremental Learning — 2× in this paper
• Benchmark — 1× in this paper · explained in 2 episodes
• Catastrophic Forgetting — 1× in this paper · explained in 6 episodes

Sources

• MixMatch: A Holistic Approach to Semi-Supervised Learning
• Make Domain Shift a Catastrophic Forgetting Alleviator in Class-Incremental Learning
• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Preventing Zero-Shot Transfer Degradation in Continual Learning of Vision-Language Models

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models