Accurate and Fast Pixel Retrieval with Spatial and Uncertainty Aware Hypergraph Diffusion
This work addresses the need for accurate and fast object localization in content-based image retrieval, particularly for real-world applications requiring trade-offs between speed and precision, representing a notable but incremental advancement.
The paper tackled the problem of inefficient spatial information propagation in traditional diffusion methods for image and pixel retrieval by introducing a hypergraph-based framework with community selection, achieving state-of-the-art accuracy on PROxford and PRParis datasets while maintaining fast processing speed.
This paper presents a novel method designed to enhance the efficiency and accuracy of both image retrieval and pixel retrieval. Traditional diffusion methods struggle to propagate spatial information effectively in conventional graphs due to their reliance on scalar edge weights. To overcome this limitation, we introduce a hypergraph-based framework, uniquely capable of efficiently propagating spatial information using local features during query time, thereby accurately retrieving and localizing objects within a database. Additionally, we innovatively utilize the structural information of the image graph through a technique we term "community selection". This approach allows for the assessment of the initial search result's uncertainty and facilitates an optimal balance between accuracy and speed. This is particularly crucial in real-world applications where such trade-offs are often necessary. Our experimental results, conducted on the (P)ROxford and (P)RParis datasets, demonstrate the significant superiority of our method over existing diffusion techniques. We achieve state-of-the-art (SOTA) accuracy in both image-level and pixel-level retrieval, while also maintaining impressive processing speed. This dual achievement underscores the effectiveness of our hypergraph-based framework and community selection technique, marking a notable advancement in the field of content-based image retrieval.