AI RESEARCH
LoFT: Parameter-Efficient Fine-Tuning for Long-tailed Semi-Supervised Learning in Open-World Scenarios
arXiv CS.LG
•
ArXi:2509.09926v4 Announce Type: replace Long-tailed semi-supervised learning (LTSSL) presents a formidable challenge where models must overcome the scarcity of tail samples while mitigating the noise from unreliable pseudo-labels. Most prior LTSSL methods are designed to train models from scratch, which often leads to issues such as overconfidence and low-quality pseudo-labels.