Centroid Based Concept Learning for RGB-D Indoor Scene Classification

Abstract

This paper contributes a novel cognitively-inspired method for RGB-D indoor scene classification. High intra-class variance and low inter-class variance make indoor scene classification an extremely challenging task. To cope with this problem, we propose a clustering approach inspired by the concept learning model of the hippocampus and the neocortex, to generate clusters and centroids for different scene categories. Test images depicting different scenes are classified by using their distance to the closest centroids (concepts). Modeling of RGB-D scenes as centroids not only leads to state-of-the-art classification performance on benchmark datasets (SUN RGB-D and NYU Depth V2), but also offers a method for inspecting and interpreting the space of centroids. Inspection of the centroids generated by our approach on RGB-D datasets leads us to propose a method for merging conceptually similar categories, resulting in improved accuracy for all approaches.

arXiv commentAccepted at BMVC 2020

References in corpus (6)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Clustering with Deep Learning: Taxonomy and New Methods
• Exploiting Local Features from Deep Networks for Image Retrieval
• Cognitively-Inspired Model for Incremental Learning Using a Few Examples
• Storing Encoded Episodes as Concepts for Continual Learning

Cited by in corpus (6)

• Cognitively-Inspired Model for Incremental Learning Using a Few Examples
• Deep Learning for Scene Classification: A Survey
• Storing Encoded Episodes as Concepts for Continual Learning
• F-SIOL-310: A Robotic Dataset and Benchmark for Few-Shot Incremental Object Learning
• CBCL-PR: A Cognitively Inspired Model for Class-Incremental Learning in Robotics
• Learning Novel Objects Continually Through Curiosity