Unsupervised Semantic-based Aggregation Of Deep Convolutional Features

Abstract

In this paper, we propose a simple but effective semantic-based aggregation (SBA) method. The proposed SBA utilizes the discriminative filters of deep convolutional layers as semantic detectors. Moreover, we propose the effective unsupervised strategy to select some semantic detectors to generate the "probabilistic proposals", which highlight certain discriminative pattern of objects and suppress the noise of background. The final global SBA representation could then be acquired by aggregating the regional representations weighted by the selected "probabilistic proposals" corresponding to various semantic content. Our unsupervised SBA is easy to generalize and achieves excellent performance on various tasks. We conduct comprehensive experiments and show that our unsupervised SBA outperforms the state-of-the-art unsupervised and supervised aggregation methods on image retrieval, place recognition and cloud classification.

Stats

• citations37
• S2 citations—
• github stars0
• HF likes0
• heat score11.85
• arxiv keyxu2018unsupervised

Related papers

• Unsupervised Part-based Weighting Aggregation Of Deep Convolutional Features For Image Retrieval (2017)14.91
• Selective Convolutional Descriptor Aggregation For Fine-grained Image Retrieval (2016)19.37
• Adaptive Co-weighting Deep Convolutional Features For Object Retrieval (2018)4.52
• Adversarial Soft-detection-based Aggregation Network For Image Retrieval (2018)0.00
• Unsupervised Semantic Deep Hashing (2018)10.48
• Aggregating Binary Local Descriptors For Image Retrieval (2016)7.16
• Simultaneous Feature Aggregating And Hashing For Large-scale Image Search (2017)10.61
• Co-occurrence Of Deep Convolutional Features For Image Search (2020)9.76