愿遗忘与你同在：针对带噪声标签学习的交替重放
May the Forgetting Be with You: Alternate Replay for Learning with Noisy Labels
AI总结：
针对带噪声标签的持续学习问题，提出交替经验回放（AER）方法，利用遗忘机制区分干净、复杂与噪声样本，并结合非对称平衡采样（ABS）策略提升缓冲区纯度，较现有方法准确率平均提升4.71个百分点。
摘要：
遗忘在增量训练中构成了重大挑战，使得当代AI系统在流数据环境中吸收新知识变得尤为困难。为解决这一问题，持续学习（CL）中的大多数方法依赖于对过去数据的有限缓冲区进行重放。然而，现实场景中存在的噪声（由于人工标注受时间限制或数据自动从网络收集）经常使这些策略变得脆弱。在本研究中，我们通过引入交替经验回放（AER）来解决带噪声标签的持续学习（CLN）问题，该方法利用遗忘机制在内存缓冲区中保持干净样本、复杂样本和噪声样本之间的清晰区分。其核心思想是，那些难以适应先前学习数据分布的复杂或错误标注样本最有可能被遗忘。为了充分利用这种分离的优势，我们为AER配备了非对称平衡采样（ABS）：这是一种新的样本选择策略，它在当前任务上优先保证纯度，同时保留过去的相关样本。通过广泛的计算比较，我们证明了该方法在所得缓冲区的准确性和纯度方面的有效性，与现有的基于损失的净化策略相比，准确率平均提升了4.71个百分点。代码可在https://github.com/aimagelab/mammoth获取。
英文摘要：
Forgetting presents a significant challenge during incremental training, making it particularly demanding for contemporary AI systems to assimilate new knowledge in streaming data environments. To address this issue, most approaches in Continual Learning (CL) rely on the replay of a restricted buffer of past data. However, the presence of noise in real-world scenarios, where human annotation is constrained by time limitations or where data is automatically gathered from the web, frequently renders these strategies vulnerable. In this study, we address the problem of CL under Noisy Labels (CLN) by introducing Alternate Experience Replay (AER), which takes advantage of forgetting to maintain a clear distinction between clean, complex, and noisy samples in the memory buffer. The idea is that complex or mislabeled examples, which hardly fit the previously learned data distribution, are most likely to be forgotten. To grasp the benefits of such a separation, we equip AER with Asymmetric Balanced Sampling (ABS): a new sample selection strategy that prioritizes purity on the current task while retaining relevant samples from the past. Through extensive computational comparisons, we demonstrate the effectiveness of our approach in terms of both accuracy and purity of the obtained buffer, resulting in a remarkable average gain of 4.71% points in accuracy with respect to existing loss-based purification strategies. Code is available at https://github.com/aimagelab/mammoth.
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。
