Unsupervised Part-based Weighting Aggregation of Deep Convolutional Features for Image Retrieval
Preprint
Abstract
In this paper, we propose a simple but effective semantic part-based weighting aggregation (PWA) for image retrieval. The proposed PWA utilizes the discriminative filters of deep convolutional layers as part detectors. Moreover, we propose the effective unsupervised strategy to select some part detectors to generate the "probabilistic proposals", which highlight certain discriminative parts of objects and suppress the noise of background. The final global PWA representation could then be acquired by aggregating the regional representations weighted by the selected "probabilistic proposals" corresponding to various semantic content. We conduct comprehensive experiments on four standard datasets and show that our unsupervised PWA outperforms the state-of-the-art unsupervised and supervised aggregation methods. Code is available at https://github.com/XJhaoren/PWA.Keywords
All Related Versions
This publication has 9 references indexed in Scilit:
- Iterative Manifold Embedding Layer Learned by Incomplete Data for Large-Scale Image RetrievalIEEE Transactions on Multimedia, 2018
- Selective Convolutional Descriptor Aggregation for Fine-Grained Image RetrievalIEEE Transactions on Image Processing, 2017
- Weakly Supervised Learning of Part Selection Model with Spatial Constraints for Fine-Grained Image ClassificationProceedings of the AAAI Conference on Artificial Intelligence, 2017
- Improving Large-Scale Image Retrieval Through Robust Aggregation of Local DescriptorsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Weakly Supervised Fine-Grained Categorization With Part-Based Image RepresentationIEEE Transactions on Image Processing, 2016
- Fast Object Retrieval Using Direct Spatial MatchingIEEE Transactions on Multimedia, 2015
- The Inverted Multi-IndexIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- Selective Search for Object RecognitionInternational Journal of Computer Vision, 2013
- Aggregating Local Image Descriptors into Compact CodesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2011