LoFT uses parameter-efficient fine-tuning of foundation models for long-tailed semi-supervised learning, supported by proofs that this reduces hypothesis complexity to minimize balanced posterior error and compresses outlier acceptance regions, with LoFT-OW handling open-world OOD cases.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Prototype-based interpretable classifier developed for MSL Mars images to enable explained content-based search on the PDS Image Atlas.
citing papers explorer
-
LoFT: Parameter-Efficient Fine-Tuning for Long-tailed Semi-Supervised Learning in Open-World Scenarios
LoFT uses parameter-efficient fine-tuning of foundation models for long-tailed semi-supervised learning, supported by proofs that this reduces hypothesis complexity to minimize balanced posterior error and compresses outlier acceptance regions, with LoFT-OW handling open-world OOD cases.
-
Interactive Mars Image Content-Based Search with Interpretable Machine Learning
Prototype-based interpretable classifier developed for MSL Mars images to enable explained content-based search on the PDS Image Atlas.