Unsupervised Part-based Weighting Aggregation Of Deep Convolutional Features For Image Retrieval

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.

Stats

• citations34
• S2 citations—
• github stars45
• HF likes0
• heat score14.91
• arxiv keyxu2017unsupervised

Code

• XJhaoren/PWA—

Related papers

• Adaptive Co-weighting Deep Convolutional Features For Object Retrieval (2018)4.52
• Unsupervised Semantic-based Aggregation Of Deep Convolutional Features (2018)11.85
• Selective Convolutional Descriptor Aggregation For Fine-grained Image Retrieval (2016)19.37
• Probability Weighted Compact Feature For Domain Adaptive Retrieval (2020)15.19
• Deep Image Retrieval: Learning Global Representations For Image Search (2016)19.67
• Adversarial Soft-detection-based Aggregation Network For Image Retrieval (2018)0.00
• Beyond Part Models: Person Retrieval With Refined Part Pooling (and A Strong Convolutional Baseline) (2017)24.30
• Aggregated Deep Local Features For Remote Sensing Image Retrieval (2019)14.11