SEDEG：解码器和编码器通用性的逐步增强用于具有小内存的类别增量学习
SEDEG:Sequential Enhancement of Decoder and Encoder's Generality for Class Incremental Learning with Small Memory
AI总结：
SEDEG通过两阶段训练框架提升视觉Transformer中解码器和编码器的通用性，以应对动态数据输入，减少灾难性遗忘，实验表明其在小内存场景下表现优异。
摘要：
在增量学习中，增强知识的通用性对于适应动态数据输入至关重要。它可以开发通用的表示或更平衡的决策边界，防止长期知识退化，从而减轻灾难性遗忘。一些新兴的增量学习方法采用编码器-解码器架构并取得了有希望的结果。在编码器-解码器架构中，提高编码器和解码器的泛化能力是关键，因为它有助于保留先前学习的知识，同时确保适应性和对新多样数据输入的鲁棒性。然而，许多现有的连续方法只专注于增强其中的一个组件，这限制了它们在减轻灾难性遗忘方面的有效性。并且这些方法在小内存场景中表现更差，其中只能存储有限的历史样本。为了缓解这一限制，我们引入了SEDEG，一种针对视觉Transformer（ViT）的两阶段训练框架，重点是逐步提高解码器和编码器的通用性。最初，SEDEG通过特征提升训练一个集成的编码器以学习通用的表示，随后增强解码器的通用性和平衡分类器。下一阶段涉及使用知识蒸馏（KD）策略来压缩集成的编码器并开发一个新的、更通用的编码器。这包括使用平衡的KD方法和特征KD进行有效的知识转移。在三个基准数据集上的广泛实验表明了SEDEG的优越性能，消融研究证实了其组件的有效性。代码可在https://github.com/ShaolingPu/CIL获取。
英文摘要：
In incremental learning, enhancing the generality of knowledge is crucial for adapting to dynamic data inputs. It can develop generalized representations or more balanced decision boundaries, preventing the degradation of long-term knowledge over time and thus mitigating catastrophic forgetting. Some emerging incremental learning methods adopt an encoder-decoder architecture and have achieved promising results. In the encoder-decoder achitecture, improving the generalization capabilities of both the encoder and decoder is critical, as it helps preserve previously learned knowledge while ensuring adaptability and robustness to new, diverse data inputs. However, many existing continual methods focus solely on enhancing one of the two components, which limits their effectiveness in mitigating catastrophic forgetting. And these methods perform even worse in small-memory scenarios, where only a limited number of historical samples can be stored. To mitigate this limitation, we introduces SEDEG, a two-stage training framework for vision transformers (ViT), focusing on sequentially improving the generality of both Decoder and Encoder. Initially, SEDEG trains an ensembled encoder through feature boosting to learn generalized representations, which subsequently enhance the decoder's generality and balance the classifier. The next stage involves using knowledge distillation (KD) strategies to compress the ensembled encoder and develop a new, more generalized encoder. This involves using a balanced KD approach and feature KD for effective knowledge transfer. Extensive experiments on three benchmark datasets show SEDEG's superior performance, and ablation studies confirm the efficacy of its components. The code is available at https://github.com/ShaolingPu/CIL.
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。
