SRRM: Semantic Region Relation Model for Indoor Scene Recognition

TL;DR

The paper introduces SRRM, a novel model that leverages semantic region relationships for improved indoor scene recognition, combining it with PlacesCNN to outperform state-of-the-art methods on multiple datasets.

Contribution

It proposes the SRRM model that directly models semantic region relationships and combines it with PlacesCNN for enhanced indoor scene recognition.

Findings

CSRRM outperforms SOTA methods on MIT Indoor 67

Significant improvement on reduced Places365 dataset

Effective exploitation of semantic relationships without retraining

Abstract

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