Unsupervised Semantic-based Aggregation of Deep Convolutional Features

04/03/2018
by   Jian Xu, et al.
0

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.

READ FULL TEXT
research
05/03/2017

Unsupervised Part-based Weighting Aggregation of Deep Convolutional Features for Image Retrieval

In this paper, we propose a simple but effective semantic part-based wei...
research
11/19/2018

Weakly Supervised Soft-detection-based Aggregation Method for Image Retrieval

In recent year, the compact representations based on activations of Conv...
research
09/20/2019

Deep Aggregation of Regional Convolutional Activations for Content Based Image Retrieval

One of the key challenges of deep learning based image retrieval remains...
research
08/01/2018

Attention-based Pyramid Aggregation Network for Visual Place Recognition

Visual place recognition is challenging in the urban environment and is ...
research
07/12/2019

ACTNET: end-to-end learning of feature activations and multi-stream aggregation for effective instance image retrieval

We propose a novel CNN architecture called ACTNET for robust instance im...
research
03/20/2018

Adaptive Co-weighting Deep Convolutional Features For Object Retrieval

Aggregating deep convolutional features into a global image vector has a...
research
06/14/2019

Fusion vectors: Embedding Graph Fusions for Efficient Unsupervised Rank Aggregation

The vast increase in amount and complexity of digital content led to a w...

Please sign up or login with your details

Forgot password? Click here to reset