# Cross-dimensional Weighting for Aggregated Deep Convolutional Features

arXiv: https://arxiv.org/abs/1512.04065 · HTML: https://mlsanity.com/paper/1512.04065/

## Key facts

- Cited by 42 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Dec 2015.

## Built on by (most cited first, 30 of 42)

- [TransVPR: Transformer-based place recognition with multi-level attention aggregation](https://mlsanity.com/paper/2201.02001/) (2022)
- [Deep Learning for Instance Retrieval: A Survey](https://mlsanity.com/paper/2101.11282/) (2021)
- [Unsupervised Object Localization: Observing the Background to Discover Objects](https://mlsanity.com/paper/2212.07834/) (2022)
- [Instance-level Image Retrieval using Reranking Transformers](https://mlsanity.com/paper/2103.12236/) (2021)
- [Global Features are All You Need for Image Retrieval and Reranking](https://mlsanity.com/paper/2308.06954/) (2023)
- [Investigating the Role of Image Retrieval for Visual Localization -- An exhaustive benchmark](https://mlsanity.com/paper/2205.15761/) (2022)
- [Compatibility-aware Heterogeneous Visual Search](https://mlsanity.com/paper/2105.06047/) (2021)
- [Target before Shooting: Accurate Anomaly Detection and Localization under One Millisecond via Cascade Patch Retrieval](https://mlsanity.com/paper/2308.06748/) (2023)
- [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)
- [Keep It SimPool: Who Said Supervised Transformers Suffer from Attention Deficit?](https://mlsanity.com/paper/2309.06891/) (2023)
- [All the attention you need: Global-local, spatial-channel attention for image retrieval](https://mlsanity.com/paper/2107.08000/) (2021)
- [SERE: Exploring Feature Self-relation for Self-supervised Transformer](https://mlsanity.com/paper/2206.05184/) (2022)
- [Investigating the Vision Transformer Model for Image Retrieval Tasks](https://mlsanity.com/paper/2101.03771/) (2021)
- [SLOSH: Set LOcality Sensitive Hashing via Sliced-Wasserstein Embeddings](https://mlsanity.com/paper/2112.05872/) (2021)
- [MTLDesc: Looking Wider to Describe Better](https://mlsanity.com/paper/2203.07003/) (2022)
- [EDEN: Deep Feature Distribution Pooling for Saimaa Ringed Seals Pattern Matching](https://mlsanity.com/paper/2105.13979/) (2021)
- [Local Propagation for Few-Shot Learning](https://mlsanity.com/paper/2101.01480/) (2021)
- [Group Generalized Mean Pooling for Vision Transformer](https://mlsanity.com/paper/2212.04114/) (2022)
- [On Train-Test Class Overlap and Detection for Image Retrieval](https://mlsanity.com/paper/2404.01524/) (2024)
- [Exploiting CLIP-based Multi-modal Approach for Artwork Classification and Retrieval](https://mlsanity.com/paper/2309.12110/) (2023)
- [Structure Similarity Preservation Learning for Asymmetric Image Retrieval](https://mlsanity.com/paper/2403.00648/) (2024)
- [LVLM-empowered Multi-modal Representation Learning for Visual Place Recognition](https://mlsanity.com/paper/2407.06730/) (2024)
- [Learning Regional Attention over Multi-resolution Deep Convolutional Features for Trademark Retrieval](https://mlsanity.com/paper/2104.07240/) (2021)
- [Towards Accurate Localization by Instance Search](https://mlsanity.com/paper/2107.05005/) (2021)
- [Why Out-of-distribution Detection in CNNs Does Not Like Mahalanobis -- and What to Use Instead](https://mlsanity.com/paper/2110.07043/) (2021)
- [Instance Image Retrieval by Learning Purely From Within the Dataset](https://mlsanity.com/paper/2208.06119/) (2022)
- [Generalized Sum Pooling for Metric Learning](https://mlsanity.com/paper/2308.09228/) (2023)
- [SupScene: Scene-Structured Overlap Supervision for Image Retrieval in Unconstrained SfM](https://mlsanity.com/paper/2601.11930/) (2026)
- [CBIR using Pre-Trained Neural Networks](https://mlsanity.com/paper/2110.14455/) (2021)

## Abstract (arXiv)

We propose a simple and straightforward way of creating powerful image representations via cross-dimensional weighting and aggregation of deep convolutional neural network layer outputs. We first present a generalized framework that encompasses a broad family of approaches and includes cross-dimensional pooling and weighting steps. We then propose specific non-parametric schemes for both spatial- and channel-wise weighting that boost the effect of highly active spatial responses and at the same time regulate burstiness effects. We experiment on different public datasets for image search and show that our approach outperforms the current state-of-the-art for approaches based on pre-trained networks. We also provide an easy-to-use, open source implementation that reproduces our results.