LoFT: Parameter-Efficient Fine-Tuning for Long-tailed Semi-Supervised Learning in Open-World Scenarios
This addresses the challenge of imbalanced and open-world data in real-world applications, offering an incremental improvement over existing LTSSL methods.
The paper tackled the problem of long-tailed semi-supervised learning by proposing LoFT, a parameter-efficient fine-tuning framework that leverages foundation models to generate reliable pseudo-labels, achieving superior performance on benchmarks with only 1% of unlabeled data compared to prior methods.
Long-tailed learning has garnered increasing attention due to its wide applicability in real-world scenarios. Among existing approaches, Long-Tailed Semi-Supervised Learning (LTSSL) has emerged as an effective solution by incorporating a large amount of unlabeled data into the imbalanced labeled dataset. However, most prior LTSSL methods are designed to train models from scratch, which often leads to issues such as overconfidence and low-quality pseudo-labels. To address these challenges, we extend LTSSL into the foundation model fine-tuning paradigm and propose a novel framework: LoFT (Long-tailed semi-supervised learning via parameter-efficient Fine-Tuning). We demonstrate that fine-tuned foundation models can generate more reliable pseudolabels, thereby benefiting imbalanced learning. Furthermore, we explore a more practical setting by investigating semi-supervised learning under open-world conditions, where the unlabeled data may include out-of-distribution (OOD) samples. To handle this problem, we propose LoFT-OW (LoFT under Open-World scenarios) to improve the discriminative ability. Experimental results on multiple benchmarks demonstrate that our method achieves superior performance compared to previous approaches, even when utilizing only 1\% of the unlabeled data compared with previous works.