# Scene Retrieval for Contextual Visual Mapping

arXiv: https://arxiv.org/abs/2102.12728 · HTML: https://mlsanity.com/paper/2102.12728/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 36 references that are in the map.
- First posted on arXiv 25 Feb 2021.

## Builds on (most cited first, 17 of 17)

- [YOLO9000: Better, Faster, Stronger](https://mlsanity.com/paper/1612.08242/) (2016)
- [NetVLAD: CNN architecture for weakly supervised place recognition](https://mlsanity.com/paper/1511.07247/) (2015)
- [Deep metric learning using Triplet network](https://mlsanity.com/paper/1412.6622/) (2014)
- [A Survey of Autonomous Driving: Common Practices and Emerging Technologies](https://mlsanity.com/paper/1906.05113/) (2019)
- [Deep Learning Features at Scale for Visual Place Recognition](https://mlsanity.com/paper/1701.05105/) (2017)
- [A Holistic Visual Place Recognition Approach using Lightweight CNNs for Significant ViewPoint and Appearance Changes](https://mlsanity.com/paper/1811.03032/) (2018)
- [Multi-scale recognition with DAG-CNNs](https://mlsanity.com/paper/1505.05232/) (2015)
- [Memorable Maps: A Framework for Re-defining Places in Visual Place Recognition](https://mlsanity.com/paper/1811.03529/) (2018)
- [Levelling the Playing Field: A Comprehensive Comparison of Visual Place Recognition Approaches under Changing Conditions](https://mlsanity.com/paper/1903.09107/) (2019)
- [DEDUCE: Diverse scEne Detection methods in Unseen Challenging Environments](https://mlsanity.com/paper/1908.00191/) (2019)
- [Look No Deeper: Recognizing Places from Opposing Viewpoints under Varying Scene Appearance using Single-View Depth Estimation](https://mlsanity.com/paper/1902.07381/) (2019)
- [Attention-Aware Age-Agnostic Visual Place Recognition](https://mlsanity.com/paper/1909.05163/) (2019)
- [Are State-of-the-art Visual Place Recognition Techniques any Good for Aerial Robotics?](https://mlsanity.com/paper/1904.07967/) (2019)
- [FOSNet: An End-to-End Trainable Deep Neural Network for Scene Recognition](https://mlsanity.com/paper/1907.07570/) (2019)
- [CAMAL: Context-Aware Multi-layer Attention framework for Lightweight Environment Invariant Visual Place Recognition](https://mlsanity.com/paper/1909.08153/) (2019)
- [Filter Early, Match Late: Improving Network-Based Visual Place Recognition](https://mlsanity.com/paper/1906.12176/) (2019)
- [Class Anchor Clustering: a Loss for Distance-based Open Set Recognition](https://mlsanity.com/paper/2004.02434/) (2020)

## Abstract (arXiv)

Visual navigation localizes a query place image against a reference database of place images, also known as a `visual map'. Localization accuracy requirements for specific areas of the visual map, `scene classes', vary according to the context of the environment and task. State-of-the-art visual mapping is unable to reflect these requirements by explicitly targetting scene classes for inclusion in the map. Four different scene classes, including pedestrian crossings and stations, are identified in each of the Nordland and St. Lucia datasets. Instead of re-training separate scene classifiers which struggle with these overlapping scene classes we make our first contribution: defining the problem of `scene retrieval'. Scene retrieval extends image retrieval to classification of scenes defined at test time by associating a single query image to reference images of scene classes. Our second contribution is a triplet-trained convolutional neural network (CNN) to address this problem which increases scene classification accuracy by up to 7% against state-of-the-art networks pre-trained for scene recognition. The second contribution is an algorithm `DMC' that combines our scene classification with distance and memorability for visual mapping. Our analysis shows that DMC includes 64% more images of our chosen scene classes in a visual map than just using distance interval mapping. State-of-the-art visual place descriptors AMOS-Net, Hybrid-Net and NetVLAD are finally used to show that DMC improves scene class localization accuracy by a mean of 3% and localization accuracy of the remaining map images by a mean of 10% across both datasets.