# DenserNet: Weakly Supervised Visual Localization Using Multi-scale Feature Aggregation

arXiv: https://arxiv.org/abs/2012.02366 · HTML: https://mlsanity.com/paper/2012.02366/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Dec 2020.

## Built on by (most cited first, 30 of 33)

- [EigenPlaces: Training Viewpoint Robust Models for Visual Place Recognition](https://mlsanity.com/paper/2308.10832/) (2023)
- [Deep Visual Geo-localization Benchmark](https://mlsanity.com/paper/2204.03444/) (2022)
- [Where is your place, Visual Place Recognition?](https://mlsanity.com/paper/2103.06443/) (2021)
- [AutoMix: Unveiling the Power of Mixup for Stronger Classifiers](https://mlsanity.com/paper/2103.13027/) (2021)
- [Physical Attack on Monocular Depth Estimation with Optimal Adversarial Patches](https://mlsanity.com/paper/2207.04718/) (2022)
- [MAVE: A Product Dataset for Multi-source Attribute Value Extraction](https://mlsanity.com/paper/2112.08663/) (2021)
- [TF-Blender: Temporal Feature Blender for Video Object Detection](https://mlsanity.com/paper/2108.05821/) (2021)
- [CLUSTSEG: Clustering for Universal Segmentation](https://mlsanity.com/paper/2305.02187/) (2023)
- [Adaptive Assignment for Geometry Aware Local Feature Matching](https://mlsanity.com/paper/2207.08427/) (2022)
- [Adaptive Spot-Guided Transformer for Consistent Local Feature Matching](https://mlsanity.com/paper/2303.16624/) (2023)
- [Are Local Features All You Need for Cross-Domain Visual Place Recognition?](https://mlsanity.com/paper/2304.05887/) (2023)
- [Learning Equivariant Segmentation with Instance-Unique Querying](https://mlsanity.com/paper/2210.00911/) (2022)
- [Adversarial Training of Self-supervised Monocular Depth Estimation against Physical-World Attacks](https://mlsanity.com/paper/2301.13487/) (2023)
- [Solve the Puzzle of Instance Segmentation in Videos: A Weakly Supervised Framework with Spatio-Temporal Collaboration](https://mlsanity.com/paper/2212.07592/) (2022)
- [FAQ: Feature Aggregated Queries for Transformer-based Video Object Detectors](https://mlsanity.com/paper/2303.08319/) (2023)
- [Poly-CAM: High resolution class activation map for convolutional neural networks](https://mlsanity.com/paper/2204.13359/) (2022)
- [EDTformer: An Efficient Decoder Transformer for Visual Place Recognition](https://mlsanity.com/paper/2412.00784/) (2024)
- [CML-MOTS: Collaborative Multi-task Learning for Multi-Object Tracking and Segmentation](https://mlsanity.com/paper/2311.00987/) (2023)
- [GeoSegNet: Point Cloud Semantic Segmentation via Geometric Encoder-Decoder Modeling](https://mlsanity.com/paper/2207.06766/) (2022)
- [Towards Unbiased Label Distribution Learning for Facial Pose Estimation Using Anisotropic Spherical Gaussian](https://mlsanity.com/paper/2208.09122/) (2022)
- [ClusterFormer: Clustering As A Universal Visual Learner](https://mlsanity.com/paper/2309.13196/) (2023)
- [DFA: Dynamic Feature Aggregation for Efficient Video Object Detection](https://mlsanity.com/paper/2210.00588/) (2022)
- [Deep Homography Estimation for Visual Place Recognition](https://mlsanity.com/paper/2402.16086/) (2024)
- [Survey and Systematization of 3D Object Detection Models and Methods](https://mlsanity.com/paper/2201.09354/) (2022)
- [Self-Reference Deep Adaptive Curve Estimation for Low-Light Image Enhancement](https://mlsanity.com/paper/2308.08197/) (2023)
- [SSGA-Net: Stepwise Spatial Global-local Aggregation Networks for for Autonomous Driving](https://mlsanity.com/paper/2405.18857/) (2024)
- [Radiance Field Learners As UAV First-Person Viewers](https://mlsanity.com/paper/2408.05533/) (2024)
- [LEADER: Learning Reliable Local-to-Global Correspondences for LiDAR Relocalization](https://mlsanity.com/paper/2604.11355/) (2026)
- [Heterogeneous Feature Distillation Network for SAR Image Semantic Segmentation](https://mlsanity.com/paper/2210.08988/) (2022)
- [Lightweight Improved Residual Network for Efficient Inverse Tone Mapping](https://mlsanity.com/paper/2307.03998/) (2023)

## Abstract (arXiv)

In this work, we introduce a Denser Feature Network (DenserNet) for visual localization. Our work provides three principal contributions. First, we develop a convolutional neural network (CNN) architecture which aggregates feature maps at different semantic levels for image representations. Using denser feature maps, our method can produce more keypoint features and increase image retrieval accuracy. Second, our model is trained end-to-end without pixel-level annotation other than positive and negative GPS-tagged image pairs. We use a weakly supervised triplet ranking loss to learn discriminative features and encourage keypoint feature repeatability for image representation. Finally, our method is computationally efficient as our architecture has shared features and parameters during computation. Our method can perform accurate large-scale localization under challenging conditions while remaining the computational constraint. Extensive experiment results indicate that our method sets a new state-of-the-art on four challenging large-scale localization benchmarks and three image retrieval benchmarks.