# Aggregating Deep Convolutional Features for Image Retrieval

arXiv: https://arxiv.org/abs/1510.07493 · HTML: https://mlsanity.com/paper/1510.07493/

## Key facts

- Cited by 63 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Oct 2015.

## Built on by (most cited first, 30 of 63)

- [FedProto: Federated Prototype Learning across Heterogeneous Clients](https://mlsanity.com/paper/2105.00243/) (2021)
- [Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition](https://mlsanity.com/paper/2103.01486/) (2021)
- [MixVPR: Feature Mixing for Visual Place Recognition](https://mlsanity.com/paper/2303.02190/) (2023)
- [Federated Learning from Pre-Trained Models: A Contrastive Learning Approach](https://mlsanity.com/paper/2209.10083/) (2022)
- [Where is your place, Visual Place Recognition?](https://mlsanity.com/paper/2103.06443/) (2021)
- [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)
- [DOLG: Single-Stage Image Retrieval with Deep Orthogonal Fusion of Local and Global Features](https://mlsanity.com/paper/2108.02927/) (2021)
- [Correlation Verification for Image Retrieval](https://mlsanity.com/paper/2204.01458/) (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)
- [Generalized Contrastive Optimization of Siamese Networks for Place Recognition](https://mlsanity.com/paper/2103.06638/) (2021)
- [FedAC: An Adaptive Clustered Federated Learning Framework for Heterogeneous Data](https://mlsanity.com/paper/2403.16460/) (2024)
- [Semantic Reinforced Attention Learning for Visual Place Recognition](https://mlsanity.com/paper/2108.08443/) (2021)
- [Boosting vision transformers for image retrieval](https://mlsanity.com/paper/2210.11909/) (2022)
- [(LC)2: LiDAR-Camera Loop Constraints For Cross-Modal Place Recognition](https://mlsanity.com/paper/2304.08660/) (2023)
- [Keep It SimPool: Who Said Supervised Transformers Suffer from Attention Deficit?](https://mlsanity.com/paper/2309.06891/) (2023)
- [EffoVPR: Effective Foundation Model Utilization for Visual Place Recognition](https://mlsanity.com/paper/2405.18065/) (2024)
- [LCFed: An Efficient Clustered Federated Learning Framework for Heterogeneous Data](https://mlsanity.com/paper/2501.01850/) (2025)
- [Contextual Similarity Aggregation with Self-attention for Visual Re-ranking](https://mlsanity.com/paper/2110.13430/) (2021)
- [MultiRes-NetVLAD: Augmenting Place Recognition Training with Low-Resolution Imagery](https://mlsanity.com/paper/2202.09146/) (2022)
- [All the attention you need: Global-local, spatial-channel attention for image retrieval](https://mlsanity.com/paper/2107.08000/) (2021)
- [Design Space Exploration of Low-Bit Quantized Neural Networks for Visual Place Recognition](https://mlsanity.com/paper/2312.09028/) (2023)
- [RELOCATE: A Simple Training-Free Baseline for Visual Query Localization Using Region-Based Representations](https://mlsanity.com/paper/2412.01826/) (2024)
- [FORB: A Flat Object Retrieval Benchmark for Universal Image Embedding](https://mlsanity.com/paper/2309.16249/) (2023)
- [VoxDet: Voxel Learning for Novel Instance Detection](https://mlsanity.com/paper/2305.17220/) (2023)
- [Quality-aware Selective Fusion Network for V-D-T Salient Object Detection](https://mlsanity.com/paper/2405.07655/) (2024)
- [ES-Net: Erasing Salient Parts to Learn More in Re-Identification](https://mlsanity.com/paper/2103.05918/) (2021)
- [Retrieval and Localization with Observation Constraints](https://mlsanity.com/paper/2108.08516/) (2021)
- [Retrieving Black-box Optimal Images from External Databases](https://mlsanity.com/paper/2112.14921/) (2021)

## Abstract (arXiv)

Several recent works have shown that image descriptors produced by deep convolutional neural networks provide state-of-the-art performance for image classification and retrieval problems. It has also been shown that the activations from the convolutional layers can be interpreted as local features describing particular image regions. These local features can be aggregated using aggregation approaches developed for local features (e.g. Fisher vectors), thus providing new powerful global descriptors. In this paper we investigate possible ways to aggregate local deep features to produce compact global descriptors for image retrieval. First, we show that deep features and traditional hand-engineered features have quite different distributions of pairwise similarities, hence existing aggregation methods have to be carefully re-evaluated. Such re-evaluation reveals that in contrast to shallow features, the simple aggregation method based on sum pooling provides arguably the best performance for deep convolutional features. This method is efficient, has few parameters, and bears little risk of overfitting when e.g. learning the PCA matrix. Overall, the new compact global descriptor improves the state-of-the-art on four common benchmarks considerably.