Faster R-CNN Features For Instance Search

Abstract

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.

Stats

• citations88
• S2 citations—
• github stars0
• HF likes0
• heat score14.62
• arxiv keysalvador2016faster

Related papers

• Class-weighted Convolutional Features For Visual Instance Search (2017)12.81
• Instance-level Image Retrieval Using Reranking Transformers (2021)19.00
• What Is The Best Practice For Cnns Applied To Visual Instance Retrieval? (2016)0.00
• Context Aware Query Image Representation For Particular Object Retrieval (2017)11.49
• Group Invariant Deep Representations For Image Instance Retrieval (2016)0.00
• Where To Focus: Query Adaptive Matching For Instance Retrieval Using Convolutional Feature Maps (2016)0.00
• Saliency Weighted Convolutional Features For Instance Search (2017)9.92
• SIFT Meets CNN: A Decade Survey Of Instance Retrieval (2016)20.72