DR.WILSS：基于扩散回放的弱监督持续语义分割
DR.WILSS: Diffusion-Based Replay for Weakly Supervised Continual Semantic Segmentation
浏览论文内容
中文总结 AI 辅助
DR.WILSS提出基于扩散生成回放的方法，利用语言引导和LoRA对齐，解决弱监督类增量语义分割中的灾难性遗忘，实现无需存储训练数据的最优性能。
中文摘要 AI 辅助
弱监督类增量语义分割（WILSS）旨在通过多个步骤训练分割模型，每一步引入仅需图像级监督的新概念。我们提出了DR.WILSS，一种利用基于扩散的生成式回放来解决持续学习中灾难性遗忘的创新方法。我们的框架利用语言线索引导扩散过程，采用自修复和正则化技术高效生成回放数据，以辅助学习过程。通过生成高质量的回放数据，先前学习过的类别的信息可以在持续更新过程中得以保留，这是增量学习场景中的一个关键挑战。为了进一步使回放数据的统计特征与训练样本对齐，我们对生成模型应用了LoRA。实验结果表明，该方法在多个基准和生成架构上达到了最先进的性能，同时避免了存储训练数据以及在训练过程中使用额外资源密集型工具。所提出的技术实现了训练复杂度与推理时准确率之间的最优权衡，使DR.WILSS成为实际应用中有前景的解决方案。
英文摘要
Weakly supervised class-incremental semantic segmentation (WILSS) aims to train a segmentation model over multiple steps, each introducing new concepts to be learned with only image-level supervision. We introduce DR$.$WILSS, an innovative approach to address catastrophic forgetting in continual learning using diffusion-based generative replay. Our framework leverages language clues to guide the diffusion process, employing self-inpainting and regularization techniques to efficiently produce replay data, aiding the learning process. By generating high-quality replay data, the information from previously learned classes can be preserved during continual updates, a critical challenge in incremental learning scenarios. To further align the statistics of replay data with those of training samples, we apply LoRAs to the generative model. Experimental results demonstrate state-of-the-art performance across multiple benchmarks and generative architectures, while avoiding storage of training data and the use of additional resource-demanding tools during training. The proposed technique enables an optimal tradeoff between training complexity and inference-time accuracy, making DR$.$WILSS a promising solution for real-world applications.
发表机构
- University of Padova（帕多瓦大学）
机构由 AI 辅助整理，请以论文原文为准。
