# Faster R-CNN Features for Instance Search

arXiv: https://arxiv.org/abs/1604.08893 · HTML: https://mlsanity.com/paper/1604.08893/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Apr 2016.

## Built on by (most cited first, 14 of 14)

- [SAT: 2D Semantics Assisted Training for 3D Visual Grounding](https://mlsanity.com/paper/2105.11450/) (2021)
- [Deep Learning for Instance Retrieval: A Survey](https://mlsanity.com/paper/2101.11282/) (2021)
- [Look Around and Refer: 2D Synthetic Semantics Knowledge Distillation for 3D Visual Grounding](https://mlsanity.com/paper/2211.14241/) (2022)
- [ScanFormer: Referring Expression Comprehension by Iteratively Scanning](https://mlsanity.com/paper/2406.18048/) (2024)
- [Referring Expression Comprehension Using Language Adaptive Inference](https://mlsanity.com/paper/2306.04451/) (2023)
- [Self-paced Multi-grained Cross-modal Interaction Modeling for Referring Expression Comprehension](https://mlsanity.com/paper/2204.09957/) (2022)
- [Weakly-Supervised 3D Visual Grounding based on Visual Language Alignment](https://mlsanity.com/paper/2312.09625/) (2023)
- [On Train-Test Class Overlap and Detection for Image Retrieval](https://mlsanity.com/paper/2404.01524/) (2024)
- [Towards Accurate Localization by Instance Search](https://mlsanity.com/paper/2107.05005/) (2021)
- [FasterVideo: Efficient Online Joint Object Detection And Tracking](https://mlsanity.com/paper/2204.07394/) (2022)
- [Indicative Image Retrieval: Turning Blackbox Learning into Grey](https://mlsanity.com/paper/2201.11898/) (2022)
- [MARs: Multi-view Attention Regularizations for Patch-based Feature Recognition of Space Terrain](https://mlsanity.com/paper/2410.05182/) (2024)
- [LSVG: Language-Guided Scene Graphs with 2D-Assisted Multi-Modal Encoding for 3D Visual Grounding](https://mlsanity.com/paper/2505.04058/) (2025)
- [Class Agnostic Instance-level Descriptor for Visual Instance Search](https://mlsanity.com/paper/2506.16745/) (2025)

## Abstract (arXiv)

Image representations derived from pre-trained Convolutional Neural Networks (CNNs) have become the new state of the art in computer vision tasks such as instance retrieval. This work explores the suitability for instance retrieval of image- and region-wise representations pooled from an object detection CNN such as Faster R-CNN. We take advantage of the object proposals learned by a Region Proposal Network (RPN) and their associated CNN features to build an instance search pipeline composed of a first filtering stage followed by a spatial reranking. We further investigate the suitability of Faster R-CNN features when the network is fine-tuned for the same objects one wants to retrieve. We assess the performance of our proposed system with the Oxford Buildings 5k, Paris Buildings 6k and a subset of TRECVid Instance Search 2013, achieving competitive results.