原型潜在世界模型回放用于类增量学习
Prototype Latent World Model Replay for Class-Incremental Learning
AI总结：
提出无记忆框架，通过冻结的ImageNet预训练编码器将旧类存储为潜在状态分布，在新类到来时采样回放，结合轻量适配器和对比学习，显著提升类增量学习性能。
摘要：
类增量学习要求模型在学习新类的同时保留旧类的决策区域。当原始旧样本不再可用时，这很困难。我们提出原型潜在世界模型回放，一种无记忆框架，将旧类存储为稳定隐藏状态上的分布而非图像。冻结的ImageNet预训练编码器将每个图像映射到潜在状态空间。在该空间中，每个类由几个以原型为中心的分布及其类特定方差概括。当新类到来时，模型从该原型世界模型中采样旧潜在状态。然后，它使用采样的旧状态和真实新类特征训练轻量适配器和分类器。我们还在适配器空间中添加监督对比项，以促进类内紧凑性和新旧类分离。在Split CIFAR-100上，我们的方法在Inc5、Inc10和Inc20设置下优于微调，且无需存储原始样本。完整的Ours-LWM+Con模型在Inc5、Inc10和Inc20中分别将LastAcc从4.55%提升至31.64%，从9.06%提升至37.06%，从16.96%提升至43.10%。它还分别实现了45.86%、52.19%和56.18%的AvgAcc。消融和保留分析表明，稳定潜在状态回放是增益的主要来源。对比分离进一步优化了新旧几何结构。这些结果表明，原型潜在记忆保留了可重用的类状态分布，而不仅仅是拟合当前分类器。
英文摘要：
Class-incremental learning requires a model to learn new classes while preserving decision regions for old ones. This is difficult when raw old samples are no longer available. We propose Prototype Latent World Model Replay, a memory-free framework that stores old classes as distributions over stable hidden states rather than as images. A frozen ImageNet-pretrained encoder maps each image into a latent state space. In this space, each class is summarized by several prototype-centered distributions with class-specific variances. When new classes arrive, the model samples old latent states from this prototype world model. It then trains a lightweight adapter and classifier using both sampled old states and real new-class features. We also add a supervised contrastive term in the adapter space to promote intra-class compactness and old-new class separation. On Split CIFAR-100, our method improves over fine-tuning under Inc5, Inc10, and Inc20 without storing raw exemplars. The full Ours-LWM+Con model raises LastAcc from 4.55% to 31.64%, from 9.06% to 37.06%, and from 16.96% to 43.10% in Inc5, Inc10, and Inc20, respectively. It also achieves AvgAcc of 45.86%, 52.19%, and 56.18%. Ablation and retention analyses show that stable latent-state replay is the main source of the gain. Contrastive separation further refines the old-new geometry. These results suggest that prototype latent memory preserves reusable class-state distributions, rather than only fitting the current classifier.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
