Unsupervised Semantic-based Aggregation of Deep Convolutional Features
This work addresses feature aggregation for computer vision researchers, offering an unsupervised approach that outperforms existing methods, though it appears incremental as it builds on known techniques.
The paper tackles the problem of aggregating deep convolutional features for visual tasks by proposing an unsupervised semantic-based aggregation method that uses discriminative filters as semantic detectors to generate probabilistic proposals, achieving state-of-the-art performance on image retrieval, place recognition, and cloud classification.
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.