# Bags of Local Convolutional Features for Scalable Instance Search

arXiv: https://arxiv.org/abs/1604.04653 · HTML: https://mlsanity.com/paper/1604.04653/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Apr 2016.

## Built on by (most cited first, 13 of 13)

- [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)
- [The 2021 Image Similarity Dataset and Challenge](https://mlsanity.com/paper/2106.09672/) (2021)
- [Semantic Reinforced Attention Learning for Visual Place Recognition](https://mlsanity.com/paper/2108.08443/) (2021)
- [StructVPR: Distill Structural Knowledge with Weighting Samples for Visual Place Recognition](https://mlsanity.com/paper/2212.00937/) (2022)
- [Evaluating Contrastive Models for Instance-based Image Retrieval](https://mlsanity.com/paper/2104.14939/) (2021)
- [StructVPR++: Distill Structural and Semantic Knowledge with Weighting Samples for Visual Place Recognition](https://mlsanity.com/paper/2503.06601/) (2025)
- [Ghost-dil-NetVLAD: A Lightweight Neural Network for Visual Place Recognition](https://mlsanity.com/paper/2112.11679/) (2021)
- [Relational Self-supervised Distillation with Compact Descriptors for Image Copy Detection](https://mlsanity.com/paper/2405.17928/) (2024)
- [AggNet: Learning to Aggregate Faces for Group Membership Verification](https://mlsanity.com/paper/2206.08683/) (2022)
- [Learning Deep Representations via Contrastive Learning for Instance Retrieval](https://mlsanity.com/paper/2209.13832/) (2022)
- [FUSELOC: Fusing Global and Local Descriptors to Disambiguate 2D-3D Matching in Visual Localization](https://mlsanity.com/paper/2408.12037/) (2024)
- [Robust Scene Coordinate Regression via Geometrically-Consistent Global Descriptors](https://mlsanity.com/paper/2512.17226/) (2025)

## Abstract (arXiv)

This work proposes a simple instance retrieval pipeline based on encoding the convolutional features of CNN using the bag of words aggregation scheme (BoW). Assigning each local array of activations in a convolutional layer to a visual word produces an textitassignment map, a compact representation that relates regions of an image with a visual word. We use the assignment map for fast spatial reranking, obtaining object localizations that are used for query expansion. We demonstrate the suitability of the BoW representation based on local CNN features for instance retrieval, achieving competitive performance on the Oxford and Paris buildings benchmarks. We show that our proposed system for CNN feature aggregation with BoW outperforms state-of-the-art techniques using sum pooling at a subset of the challenging TRECVid INS benchmark.