Faster R-CNN Features for Instance Search
This work addresses instance search in computer vision, but it is incremental as it applies an existing method (Faster R-CNN) to a new task.
The paper tackled the problem of instance retrieval by using features from Faster R-CNN, an object detection CNN, to build a search pipeline with filtering and spatial reranking, achieving competitive results on benchmarks like Oxford Buildings 5k and Paris Buildings 6k.
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.