GPS：基于网格的补丁采样蒸馏紧凑记忆以实现高效在线类增量学习
GPS: Distilling Compact Memories via Grid-based Patch Sampling for Efficient Online Class-Incremental Learning
AI总结：
针对在线类增量学习中基于蒸馏的重放方法计算开销大的问题，提出无需可训练模型的GPS策略，通过网格补丁采样生成紧凑记忆样本，集成到现有框架后在记忆受限下平均精度提升3%-4%，计算开销小。
摘要：
在线类增量学习旨在让模型在有限访问过往数据的情况下持续适应新类别，同时缓解灾难性遗忘。基于重放的方法通过维护过往样本的小型记忆缓冲池来解决此问题，实现了具竞争力的性能。为在受限存储下有效重放，近期方法利用蒸馏数据增强记忆的信息量，但这类方法因使用双层优化常伴随显著计算开销。受这些局限启发，我们引入基于网格的补丁采样（GPS），这是一种轻量且有效的策略，无需依赖可训练模型即可蒸馏信息丰富的记忆样本。GPS通过从原始图像中采样像素子集生成信息样本，得到保留语义内容和结构信息的紧凑低分辨率表示；重放时，这些表示被重组以支持训练和评估。在大量基准测试上的实验表明，GPS可无缝集成到现有重放框架中，在记忆受限设置下平均最终精度提升3%-4%，且计算开销有限。
英文摘要：
Online class-incremental learning aims to enable models to continuously adapt to new classes with limited access to past data, while mitigating catastrophic forgetting. Replay-based methods address this by maintaining a small memory buffer of previous samples, achieving competitive performance. For effective replay under constrained storage, recent approaches leverage distilled data to enhance the informativeness of memory. However, such approaches often involve significant computational overhead due to the use of bi-level optimization. Motivated by these limitations, we introduce Grid-based Patch Sampling (GPS), a lightweight and effective strategy for distilling informative memory samples without relying on a trainable model. GPS generates informative samples by sampling a subset of pixels from the original image, yielding compact low-resolution representations that preserve both semantic content and structural information. During replay, these representations are reassembled to support training and evaluation. Experiments on extensive benchmarks demonstrate that GRS can be seamlessly integrated into existing replay frameworks, leading to 3%-4% improvements in average end accuracy under memory-constrained settings, with limited computational overhead.
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。
