An accurate retrieval through R-MAC+ descriptors for landmark recognition
arXiv:1806.08565
Abstract
The landmark recognition problem is far from being solved, but with the use of features extracted from intermediate layers of Convolutional Neural Networks (CNNs), excellent results have been obtained. In this work, we propose some improvements on the creation of R-MAC descriptors in order to make the newly-proposed R-MAC+ descriptors more representative than the previous ones. However, the main contribution of this paper is a novel retrieval technique, that exploits the fine representativeness of the MAC descriptors of the database images. Using this descriptors called "db regions" during the retrieval stage, the performance is greatly improved. The proposed method is tested on different public datasets: Oxford5k, Paris6k and Holidays. It outperforms the state-of-the- art results on Holidays and reached excellent results on Oxford5k and Paris6k, overcame only by approaches based on fine-tuning strategies.
References in corpus (7)
- Bags of Local Convolutional Features for Scalable Instance Search
- Exploiting Local Features from Deep Networks for Image Retrieval
- Deep Image Retrieval: Learning global representations for image search
- Geometric VLAD for Large Scale Image Search
- Object Level Deep Feature Pooling for Compact Image Representation
- Context Aware Query Image Representation for Particular Object Retrieval
- A location-aware embedding technique for accurate landmark recognition