解决长尾分布下持续学习的模型遗忘问题，提升稀有类别识别能力。
ViRN: Variational Inference and Distribution Trilateration for Long-Tailed Continual Representation Learning
- 用变分自编码器建模类别条件分布，缓解头部类别的偏差。
- 通过Wasserstein距离与几何融合重建尾部类别分布，实现样本高效对齐。
- 在6个基准上平均准确率提升10.24%，适合语音和图像中的稀有类别任务。
长尾数据分布下的持续学习（CL）仍是真实世界AI系统的关键挑战，模型需在不断学习新类别同时保留旧知识，却面临严重的类别不平衡问题。现有方法难以兼顾稳定性和可塑性，常在极端样本稀缺下失效。为此，我们提出ViRN，一种结合变分推理（VI）与分布三边定位的新型CL框架。首先，通过变分自编码器建模类别条件分布，减轻头部类别的偏差；其次，利用基于Wasserstein距离的邻域检索与几何融合，重建尾部类别的分布，实现样本高效的尾部表示对齐。在六个长尾分类基准上评估，包括语音（如罕见声学事件、口音）与图像任务，ViRN相比最先进方法平均准确率提升10.24%。
原文摘要 · Abstract (English)
Continual learning (CL) with long-tailed data distributions remains a critical challenge for real-world AI systems, where models must sequentially adapt to new classes while retaining knowledge of old ones, despite severe class imbalance. Existing methods struggle to balance stability and plasticity, often collapsing under extreme sample scarcity. To address this, we propose ViRN, a novel CL framework that integrates variational inference (VI) with distributional trilateration for robust long-tailed learning. First, we model class-conditional distributions via a Variational Autoencoder to mitigate bias toward head classes. Second, we reconstruct tail-class distributions via Wasserstein distance-based neighborhood retrieval and geometric fusion, enabling sample-efficient alignment of tail-class representations. Evaluated on six long-tailed classification benchmarks, including speech (e.g., rare acoustic events, accents) and image tasks, ViRN achieves a 10.24% average accuracy gain over state-of-the-art methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。