# MutualVPR: A Mutual Learning Framework for Resolving Supervision Inconsistencies via Adaptive Clustering

arXiv: https://arxiv.org/abs/2412.09199 · HTML: https://mlsanity.com/paper/2412.09199/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 34 references that are in the map.
- First posted on arXiv 12 Dec 2024.

## Builds on (most cited first, 25 of 25)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [CosFace: Large Margin Cosine Loss for Deep Face Recognition](https://mlsanity.com/paper/1801.09414/) (2018)
- [NetVLAD: CNN architecture for weakly supervised place recognition](https://mlsanity.com/paper/1511.07247/) (2015)
- [Fine-tuning CNN Image Retrieval with No Human Annotation](https://mlsanity.com/paper/1711.02512/) (2017)
- [Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition](https://mlsanity.com/paper/2103.01486/) (2021)
- [Rethinking Visual Geo-localization for Large-Scale Applications](https://mlsanity.com/paper/2204.02287/) (2022)
- [AnyLoc: Towards Universal Visual Place Recognition](https://mlsanity.com/paper/2308.00688/) (2023)
- [MixVPR: Feature Mixing for Visual Place Recognition](https://mlsanity.com/paper/2303.02190/) (2023)
- [Optimal Transport Aggregation for Visual Place Recognition](https://mlsanity.com/paper/2311.15937/) (2023)
- [EigenPlaces: Training Viewpoint Robust Models for Visual Place Recognition](https://mlsanity.com/paper/2308.10832/) (2023)
- [TransVPR: Transformer-based place recognition with multi-level attention aggregation](https://mlsanity.com/paper/2201.02001/) (2022)
- [R2Former: Unified Retrieval and Reranking Transformer for Place Recognition](https://mlsanity.com/paper/2304.03410/) (2023)
- [Deep Learning Features at Scale for Visual Place Recognition](https://mlsanity.com/paper/1701.05105/) (2017)
- [GSV-Cities: Toward Appropriate Supervised Visual Place Recognition](https://mlsanity.com/paper/2210.10239/) (2022)
- [CPlaNet: Enhancing Image Geolocalization by Combinatorial Partitioning of Maps](https://mlsanity.com/paper/1808.02130/) (2018)
- [BoQ: A Place is Worth a Bag of Learnable Queries](https://mlsanity.com/paper/2405.07364/) (2024)
- [CricaVPR: Cross-image Correlation-aware Representation Learning for Visual Place Recognition](https://mlsanity.com/paper/2402.19231/) (2024)
- [Data-efficient Large Scale Place Recognition with Graded Similarity Supervision](https://mlsanity.com/paper/2303.11739/) (2023)
- [Scalable Place Recognition Under Appearance Change for Autonomous Driving](https://mlsanity.com/paper/1908.00178/) (2019)
- [Adaptive-Attentive Geolocalization from few queries: a hybrid approach](https://mlsanity.com/paper/2010.06897/) (2020)
- [Close, But Not There: Boosting Geographic Distance Sensitivity in Visual Place Recognition](https://mlsanity.com/paper/2407.02422/) (2024)
- [Are Local Features All You Need for Cross-Domain Visual Place Recognition?](https://mlsanity.com/paper/2304.05887/) (2023)
- [Probabilistic Visual Place Recognition for Hierarchical Localization](https://mlsanity.com/paper/2105.03091/) (2021)
- [Semantic Reinforced Attention Learning for Visual Place Recognition](https://mlsanity.com/paper/2108.08443/) (2021)
- [EDTformer: An Efficient Decoder Transformer for Visual Place Recognition](https://mlsanity.com/paper/2412.00784/) (2024)

## Built on by (most cited first, 5 of 5)

- [DreamX-World 1.0: A General-Purpose Interactive World Model](https://mlsanity.com/paper/2606.16993/) (2026)
- [R2M-Bench: Evaluating Revisit Memory via Relative Consistency in Interactive Video World Models](https://mlsanity.com/paper/2608.27328/) (2026)
- [VisualDeltas: Learning Preferences from Visual Quality Perturbations](https://mlsanity.com/paper/2603.07272/) (2026)
- [From Open Waters to Enclosed Cabins: ProteusVPR for Cross-Scene Visual Place Recognition in Maritime Perception and Cabin Inspection](https://mlsanity.com/paper/2606.24234/) (2026)
- [AdaptVPR: Route-Aware Hard Positive Generation for Robust Visual Place Recognition](https://mlsanity.com/paper/2609.04369/) (2026)

## Abstract (arXiv)

Visual Place Recognition (VPR) enables robust localization through image retrieval based on learned descriptors. However, drastic appearance variations of images at the same place caused by viewpoint changes can lead to inconsistent supervision signals, thereby degrading descriptor learning. Existing methods either rely on manually defined cropping rules or labeled data for view differentiation, but they suffer from two major limitations: (1) reliance on labels or handcrafted rules restricts generalization capability; (2) even within the same view direction, occlusions can introduce feature ambiguity. To address these issues, we propose MutualVPR, a mutual learning framework that integrates unsupervised view self-classification and descriptor learning. We first group images by geographic coordinates, then iteratively refine the clusters using K-means to dynamically assign place categories without orientation labels. Specifically, we adopt a DINOv2-based encoder to initialize the clustering. During training, the encoder and clustering co-evolve, progressively separating drastic appearance variations of the same place and enabling consistent supervision. Furthermore, we find that capturing fine-grained image differences at a place enhances robustness. Experiments demonstrate that MutualVPR achieves state-of-the-art (SOTA) performance across multiple datasets, validating the effectiveness of our framework in improving view direction generalization, occlusion robustness.