自适应视觉场景理解：增量式场景图生成
Adaptive Visual Scene Understanding: Incremental Scene Graph Generation
AI总结：
针对场景图生成领域持续学习研究不足的问题，本文提出包含三种学习模式的CSEGG基准，以及RAS合成重放方法，实验证明其能提升效率、兼顾隐私与内存。
摘要：
场景图生成（SGG）通过分析图像提取关于物体及其关系的有效信息。在动态视觉世界中，人工智能系统需要持续检测新物体并建立其与已有物体的关系，这一点至关重要。近年来，大量研究聚焦于目标检测与图像识别领域的持续学习，但针对SGG中更具挑战性的持续学习问题的研究十分有限。难度提升源于物体间复杂的交互、动态关系及其相关上下文。因此，在持续学习中，SGG模型通常需要在自适应视觉场景理解过程中对场景图进行扩展、修改、保留与推理。为系统探究持续场景图生成（CSEGG），我们提出了一个包含三种学习模式的综合基准：关系增量、场景增量和关系泛化。此外，我们提出了一种名为RAS（基于合成分析的重放）的方法。该方法利用场景图，对其进行分解与重组以表示不同场景，并基于这些组合式场景图重放合成的场景。重放的合成场景可用于练习和提升SGG在已知与未知环境中的性能。我们的实验结果不仅凸显了将现有持续学习方法直接与SGG骨干网络结合所面临的挑战，还证明了所提方法的有效性，在提升CSEGG效率的同时兼顾了隐私保护与内存占用优化。所有数据与源代码均已在线公开。
英文摘要：
Scene graph generation (SGG) analyzes images to extract meaningful information about objects and their relationships. In the dynamic visual world, it is crucial for AI systems to continuously detect new objects and establish their relationships with existing ones. Recently, numerous studies have focused on continual learning within the domains of object detection and image recognition. However, a limited amount of research focuses on a more challenging continual learning problem in SGG. This increased difficulty arises from the intricate interactions and dynamic relationships among objects, and their associated contexts. Thus, in continual learning, SGG models are often required to expand, modify, retain, and reason scene graphs within the process of adaptive visual scene understanding. To systematically explore Continual Scene Graph Generation (CSEGG), we present a comprehensive benchmark comprising three learning regimes: relationship incremental, scene incremental, and relationship generalization. Moreover, we introduce a ``Replays via Analysis by Synthesis" method named RAS. This approach leverages the scene graphs, decomposes and re-composes them to represent different scenes, and replays the synthesized scenes based on these compositional scene graphs. The replayed synthesized scenes act as a means to practice and refine proficiency in SGG in known and unknown environments. Our experimental results not only highlight the challenges of directly combining existing continual learning methods with SGG backbones but also demonstrate the effectiveness of our proposed approach, enhancing CSEGG efficiency while simultaneously preserving privacy and memory usage. All data and source code are publicly available online.
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。
