Cross-dimensional Weighting for Aggregated Deep Convolutional Features

2015/12/13 by Yannis Kalantidis, Kalantidis, Yannis, Clayton Mellina +3 · 3 citations
Computer Science · #Advanced Image and Video Retrieval Techniques #Domain Adaptation and Few-Shot Learning #Multimodal Machine Learning Applications

paper · pdf · doi:10.48550/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.

Cited by

• Particular object retrieval with integral max-pooling of CNN activations
• Selective Convolutional Descriptor Aggregation for Fine-Grained Image Retrieval
• Where to Focus: Query Adaptive Matching for Instance Retrieval Using Convolutional Feature Maps
• On pattern classification with weighted dimensions

Related

• The Treasure beneath Convolutional Layers: Cross-convolutional-layer Pooling for Image Classification
• Augmenting Convolutional networks with attention-based aggregation
• Adaptive Co-weighting Deep Convolutional Features For Object Retrieval
• Aggregating Deep Convolutional Features for Image Retrieval
• Unsupervised Part-based Weighting Aggregation of Deep Convolutional Features for Image Retrieval