DRAG: Dynamic Region-Aware GCN for Privacy-Leaking Image Detection

TL;DR

This paper introduces DRAG, a novel dynamic region-aware GCN that adaptively identifies crucial regions and models their correlations for improved privacy-leaking image detection, outperforming existing methods significantly.

Contribution

The paper proposes a dynamic, region-aware graph convolutional network that considers diverse image elements and adaptively models their correlations for privacy detection.

Findings

Achieved 87% accuracy on a large privacy-leaking image dataset.

Outperformed state-of-the-art methods by 10 percentage points.

Effectively identified crucial regions including objects, textures, and scene elements.

Abstract

The daily practice of sharing images on social media raises a severe issue about privacy leakage. To address the issue, privacy-leaking image detection is studied recently, with the goal to automatically identify images that may leak privacy. Recent advance on this task benefits from focusing on crucial objects via pretrained object detectors and modeling their correlation. However, these methods have two limitations: 1) they neglect other important elements like scenes, textures, and objects beyond the capacity of pretrained object detectors; 2) the correlation among objects is fixed, but a fixed correlation is not appropriate for all the images. To overcome the limitations, we propose the Dynamic Region-Aware Graph Convolutional Network (DRAG) that dynamically finds out crucial regions including objects and other important elements, and models their correlation adaptively for each input image. To find out crucial regions, we cluster spatially-correlated feature channels into several region-aware feature maps. Further, we dynamically model the correlation with the self-attention mechanism and explore the interaction among the regions with a graph convolutional network. The DRAG achieved an accuracy of 87% on the largest dataset for privacy-leaking image detection, which is 10 percentage points higher than the state of the art. The further case study demonstrates that it found out crucial regions containing not only objects but other important elements like textures.