SRRM：面向室内场景识别的语义区域关系模型
SRRM: Semantic Region Relation Model for Indoor Scene Recognition
AI总结：
本文提出语义区域关系模型SRRM，直接从室内场景语义信息出发，通过自适应缓解语义歧义并建模语义区域关系，与PlacesCNN结合为CSRRM，在多个室内场景数据集上无需重训练即显著超越SOTA方法。
摘要：
尽管卷积神经网络在各种计算机视觉任务中取得了显著成功，但由于室内场景构成复杂，识别室内场景仍然面临重大挑战。因此，有效利用场景中的语义信息一直是推进室内场景识别的关键问题。遗憾的是，语义分割的准确性限制了现有利用语义信息方法的有效性。因此，许多这类方法仍停留在辅助标注或共现统计阶段，很少有方法直接探索场景内部语义元素之间的上下文关系。在本文中，我们提出了语义区域关系模型（SRRM），该模型直接从场景内部的语义信息出发。具体而言，SRRM采用一种自适应且高效的方法来减轻语义歧义的负面影响，然后对语义区域关系进行建模以执行场景识别。此外，为了更全面地利用场景中包含的信息，我们将所提出的SRRM与PlacesCNN模块相结合，构建了组合语义区域关系模型（CSRRM），并提出了一种新颖的信息组合方法，以有效探索二者之间的互补内容。在MIT Indoor 67、缩减版Places365数据集和SUN RGB-D上，CSRRM在无需重新训练的情况下显著优于SOTA方法。代码可在以下地址获取：https://github.com/ChuanxinSong/SRRM
英文摘要：
Despite the remarkable success of convolutional neural networks in various computer vision tasks, recognizing indoor scenes still presents a significant challenge due to their complex composition. Consequently, effectively leveraging semantic information in the scene has been a key issue in advancing indoor scene recognition. Unfortunately, the accuracy of semantic segmentation has limited the effectiveness of existing approaches for leveraging semantic information. As a result, many of these approaches remain at the stage of auxiliary labeling or co-occurrence statistics, with few exploring the contextual relationships between the semantic elements directly within the scene. In this paper, we propose the Semantic Region Relationship Model (SRRM), which starts directly from the semantic information inside the scene. Specifically, SRRM adopts an adaptive and efficient approach to mitigate the negative impact of semantic ambiguity and then models the semantic region relationship to perform scene recognition. Additionally, to more comprehensively exploit the information contained in the scene, we combine the proposed SRRM with the PlacesCNN module to create the Combined Semantic Region Relation Model (CSRRM), and propose a novel information combining approach to effectively explore the complementary contents between them. CSRRM significantly outperforms the SOTA methods on the MIT Indoor 67, reduced Places365 dataset, and SUN RGB-D without retraining. The code is available at: https://github.com/ChuanxinSong/SRRM
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。
