Inter-object Discriminative Graph Modeling for Indoor Scene Recognition

TL;DR

This paper introduces a novel graph-based method leveraging discriminative object knowledge to improve indoor scene recognition, achieving state-of-the-art results by modeling object-scene relationships interpretably.

Contribution

It proposes a new approach using Inter-Object Discriminative Prototype and Discriminative Graph Network to enhance scene features with interpretability and discriminative object relationships.

Findings

Achieves state-of-the-art performance on multiple scene datasets.

Effectively models object-scene discriminative relationships.

Demonstrates the importance of interpretability in object-assisted scene recognition.

Abstract

Variable scene layouts and coexisting objects across scenes make indoor scene recognition still a challenging task. Leveraging object information within scenes to enhance the distinguishability of feature representations has emerged as a key approach in this domain. Currently, most object-assisted methods use a separate branch to process object information, combining object and scene features heuristically. However, few of them pay attention to interpretably handle the hidden discriminative knowledge within object information. In this paper, we propose to leverage discriminative object knowledge to enhance scene feature representations. Initially, we capture the object-scene discriminative relationships from a probabilistic perspective, which are transformed into an Inter-Object Discriminative Prototype (IODP). Given the abundant prior knowledge from IODP, we subsequently construct a Discriminative Graph Network (DGN), in which pixel-level scene features are defined as nodes and the discriminative relationships between node features are encoded as edges. DGN aims to incorporate inter-object discriminative knowledge into the image representation through graph convolution and mapping operations (GCN). With the proposed IODP and DGN, we obtain state-of-the-art results on several widely used scene datasets, demonstrating the effectiveness of the proposed approach.