Adversarial Soft-detection-based Aggregation Network for Image Retrieval

TL;DR

This paper introduces a novel adversarial soft-detection-based aggregation method for image retrieval that effectively captures small object details without bounding box annotations, achieving state-of-the-art results.

Contribution

The paper proposes a new weakly supervised method combining adversarial detection and soft region proposals for improved image retrieval.

Findings

Achieves state-of-the-art performance on standard datasets.

Effectively captures small object details without bounding box annotations.

Enhances discriminative feature extraction for image retrieval.

Abstract

In recent year, the compact representations based on activations of Convolutional Neural Network (CNN) achieve remarkable performance in image retrieval. However, retrieval of some interested object that only takes up a small part of the whole image is still a challenging problem. Therefore, it is significant to extract the discriminative representations that contain regional information of the pivotal small object. In this paper, we propose a novel adversarial soft-detection-based aggregation (ASDA) method free from bounding box annotations for image retrieval, based on adversarial detector and soft region proposal layer. Our trainable adversarial detector generates semantic maps based on adversarial erasing strategy to preserve more discriminative and detailed information. Computed based on semantic maps corresponding to various discriminative patterns and semantic contents, our soft region proposal is arbitrary shape rather than only rectangle and it reflects the significance of objects. The aggregation based on trainable soft region proposal highlights discriminative semantic contents and suppresses the noise of background. We conduct comprehensive experiments on standard image retrieval datasets. Our weakly supervised ASDA method achieves state-of-the-art performance on most datasets. The results demonstrate that the proposed ASDA method is effective for image retrieval.