# Particular object retrieval with integral max-pooling of CNN activations

arXiv: https://arxiv.org/abs/1511.05879 · HTML: https://mlsanity.com/paper/1511.05879/

## Key facts

- Cited by 161 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Nov 2015.

## Built on by (most cited first, 30 of 161)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [XCiT: Cross-Covariance Image Transformers](https://mlsanity.com/paper/2106.09681/) (2021)
- [Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition](https://mlsanity.com/paper/2103.01486/) (2021)
- [A Self-Supervised Descriptor for Image Copy Detection](https://mlsanity.com/paper/2202.10261/) (2022)
- [MixVPR: Feature Mixing for Visual Place Recognition](https://mlsanity.com/paper/2303.02190/) (2023)
- [EigenPlaces: Training Viewpoint Robust Models for Visual Place Recognition](https://mlsanity.com/paper/2308.10832/) (2023)
- [Multimodal Autoregressive Pre-training of Large Vision Encoders](https://mlsanity.com/paper/2411.14402/) (2024)
- [TransVPR: Transformer-based place recognition with multi-level attention aggregation](https://mlsanity.com/paper/2201.02001/) (2022)
- [GSV-Cities: Toward Appropriate Supervised Visual Place Recognition](https://mlsanity.com/paper/2210.10239/) (2022)
- [Training Vision Transformers for Image Retrieval](https://mlsanity.com/paper/2102.05644/) (2021)
- [Deep Visual Geo-localization Benchmark](https://mlsanity.com/paper/2204.03444/) (2022)
- [Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision](https://mlsanity.com/paper/2202.08360/) (2022)
- [Deep Learning for Instance Retrieval: A Survey](https://mlsanity.com/paper/2101.11282/) (2021)
- [BoQ: A Place is Worth a Bag of Learnable Queries](https://mlsanity.com/paper/2405.07364/) (2024)
- [Instance-level Image Retrieval using Reranking Transformers](https://mlsanity.com/paper/2103.12236/) (2021)
- [SeqNet: Learning Descriptors for Sequence-based Hierarchical Place Recognition](https://mlsanity.com/paper/2102.11603/) (2021)
- [DOLG: Single-Stage Image Retrieval with Deep Orthogonal Fusion of Local and Global Features](https://mlsanity.com/paper/2108.02927/) (2021)
- [Zero-Shot Day-Night Domain Adaptation with a Physics Prior](https://mlsanity.com/paper/2108.05137/) (2021)
- [Correlation Verification for Image Retrieval](https://mlsanity.com/paper/2204.01458/) (2022)
- [Improving Point Cloud Based Place Recognition with Ranking-based Loss and Large Batch Training](https://mlsanity.com/paper/2203.00972/) (2022)
- [MinkLoc++: Lidar and Monocular Image Fusion for Place Recognition](https://mlsanity.com/paper/2104.05327/) (2021)
- [Global Features are All You Need for Image Retrieval and Reranking](https://mlsanity.com/paper/2308.06954/) (2023)
- [MetaEmbed: Scaling Multimodal Retrieval at Test-Time with Flexible Late Interaction](https://mlsanity.com/paper/2509.18095/) (2025)
- [Retrieval-Augmented Transformer for Image Captioning](https://mlsanity.com/paper/2207.13162/) (2022)
- [Viewpoint Invariant Dense Matching for Visual Geolocalization](https://mlsanity.com/paper/2109.09827/) (2021)
- [Unicom: Universal and Compact Representation Learning for Image Retrieval](https://mlsanity.com/paper/2304.05884/) (2023)
- [Learning Super-Features for Image Retrieval](https://mlsanity.com/paper/2201.13182/) (2022)
- [Interpretable Semantic Photo Geolocation](https://mlsanity.com/paper/2104.14995/) (2021)
- [PolaFormer: Polarity-aware Linear Attention for Vision Transformers](https://mlsanity.com/paper/2501.15061/) (2025)

## Abstract (arXiv)

Recently, image representation built upon Convolutional Neural Network (CNN) has been shown to provide effective descriptors for image search, outperforming pre-CNN features as short-vector representations. Yet such models are not compatible with geometry-aware re-ranking methods and still outperformed, on some particular object retrieval benchmarks, by traditional image search systems relying on precise descriptor matching, geometric re-ranking, or query expansion. This work revisits both retrieval stages, namely initial search and re-ranking, by employing the same primitive information derived from the CNN. We build compact feature vectors that encode several image regions without the need to feed multiple inputs to the network. Furthermore, we extend integral images to handle max-pooling on convolutional layer activations, allowing us to efficiently localize matching objects. The resulting bounding box is finally used for image re-ranking. As a result, this paper significantly improves existing CNN-based recognition pipeline: We report for the first time results competing with traditional methods on the challenging Oxford5k and Paris6k datasets.