# Learning Deep NBNN Representations for Robust Place Categorization

arXiv: https://arxiv.org/abs/1702.07898 · HTML: https://mlsanity.com/paper/1702.07898/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Feb 2017.

## Built on by (most cited first, 6 of 6)

- [Semantics for Robotic Mapping, Perception and Interaction: A Survey](https://mlsanity.com/paper/2101.00443/) (2021)
- [Topological Semantic Mapping by Consolidation of Deep Visual Features](https://mlsanity.com/paper/2106.12709/) (2021)
- [On the Challenges of Open World Recognitionunder Shifting Visual Domains](https://mlsanity.com/paper/2107.04461/) (2021)
- [Active Semantic Localization with Graph Neural Embedding](https://mlsanity.com/paper/2305.06141/) (2023)
- [An Image-based Approach of Task-driven Driving Scene Categorization](https://mlsanity.com/paper/2103.05920/) (2021)
- [Developing efficient transfer learning strategies for robust scene recognition in mobile robotics using pre-trained convolutional neural networks](https://mlsanity.com/paper/2107.11187/) (2021)

## Abstract (arXiv)

This paper presents an approach for semantic place categorization using data obtained from RGB cameras. Previous studies on visual place recognition and classification have shown that, by considering features derived from pre-trained Convolutional Neural Networks (CNNs) in combination with part-based classification models, high recognition accuracy can be achieved, even in presence of occlusions and severe viewpoint changes. Inspired by these works, we propose to exploit local deep representations, representing images as set of regions applying a Na"ive Bayes Nearest Neighbor (NBNN) model for image classification. As opposed to previous methods where CNNs are merely used as feature extractors, our approach seamlessly integrates the NBNN model into a fully-convolutional neural network. Experimental results show that the proposed algorithm outperforms previous methods based on pre-trained CNN models and that, when employed in challenging robot place recognition tasks, it is robust to occlusions, environmental and sensor changes.