SciLT：科学图像领域的长尾分类研究

SciLT: Long-Tailed Classification in Scientific Image Domains

April 4, 2026

作者: Jiahao Chen, Bing Su

cs.AI

摘要

长尾识别已受益于基础模型与微调范式，但现有研究与基准主要局限于自然图像领域，其预训练与微调数据分布相似。相比之下，科学图像具有独特的视觉特征和监督信号，这引发了对基础模型在此类场景下微调有效性的质疑。本研究在纯视觉与参数高效微调范式下探索科学长尾识别问题。在三个科学基准上的实验表明，微调基础模型带来的增益有限，并揭示出倒数第二层特征具有重要作用——尤其对尾部类别而言。基于这些发现，我们提出SciLT框架，通过自适应特征融合与双重监督学习利用多层级表征。通过联合利用倒数第二层与最终层特征，SciLT在头部与尾部类别间实现了均衡性能。大量实验证明，SciLT持续优于现有方法，为科学长尾识别建立了强大实用的基准，并为适应存在显著域偏移的科学数据提供了重要指导。

English

Long-tailed recognition has benefited from foundation models and fine-tuning paradigms, yet existing studies and benchmarks are mainly confined to natural image domains, where pre-training and fine-tuning data share similar distributions. In contrast, scientific images exhibit distinct visual characteristics and supervision signals, raising questions about the effectiveness of fine-tuning foundation models in such settings. In this work, we investigate scientific long-tailed recognition under a purely visual and parameter-efficient fine-tuning (PEFT) paradigm. Experiments on three scientific benchmarks show that fine-tuning foundation models yields limited gains, and reveal that penultimate-layer features play an important role, particularly for tail classes. Motivated by these findings, we propose SciLT, a framework that exploits multi-level representations through adaptive feature fusion and dual-supervision learning. By jointly leveraging penultimate- and final-layer features, SciLT achieves balanced performance across head and tail classes. Extensive experiments demonstrate that SciLT consistently outperforms existing methods, establishing a strong and practical baseline for scientific long-tailed recognition and providing valuable guidance for adapting foundation models to scientific data with substantial domain shifts.