Cross-dimensional Weighting for Aggregated Deep Convolutional Features
arXiv:1512.04065
Abstract
We propose a simple and straightforward way of creating powerful image representations via cross-dimensional weighting and aggregation of deep convolutional neural network layer outputs. We first present a generalized framework that encompasses a broad family of approaches and includes cross-dimensional pooling and weighting steps. We then propose specific non-parametric schemes for both spatial- and channel-wise weighting that boost the effect of highly active spatial responses and at the same time regulate burstiness effects. We experiment on different public datasets for image search and show that our approach outperforms the current state-of-the-art for approaches based on pre-trained networks. We also provide an easy-to-use, open source implementation that reproduces our results.
Accepted for publications at the 4th Workshop on Web-scale Vision and Social Media (VSM), ECCV 2016
Cited by in corpus (6)
- Particular object retrieval with integral max-pooling of CNN activations
- Bags of Local Convolutional Features for Scalable Instance Search
- Selective Convolutional Descriptor Aggregation for Fine-Grained Image Retrieval
- Where to Focus: Query Adaptive Matching for Instance Retrieval Using Convolutional Feature Maps
- Discriminative multi-view Privileged Information learning for image re-ranking
- Deep Shape Matching