Deep Feature Aggregation and Image Re-ranking with Heat Diffusion for Image Retrieval
This work addresses a specific bottleneck in image retrieval for computer vision applications, offering an incremental improvement over existing methods.
The paper tackles the problem of repetitive or bursty features dominating image representations in deep learning-based image retrieval, proposing an unsupervised aggregation method using heat diffusion to avoid over-representation and showing superior performance on public benchmarks.
Image retrieval based on deep convolutional features has demonstrated state-of-the-art performance in popular benchmarks. In this paper, we present a unified solution to address deep convolutional feature aggregation and image re-ranking by simulating the dynamics of heat diffusion. A distinctive problem in image retrieval is that repetitive or \emph{bursty} features tend to dominate final image representations, resulting in representations less distinguishable. We show that by considering each deep feature as a heat source, our unsupervised aggregation method is able to avoid over-representation of \emph{bursty} features. We additionally provide a practical solution for the proposed aggregation method and further show the efficiency of our method in experimental evaluation. Inspired by the aforementioned deep feature aggregation method, we also propose a method to re-rank a number of top ranked images for a given query image by considering the query as the heat source. Finally, we extensively evaluate the proposed approach with pre-trained and fine-tuned deep networks on common public benchmarks and show superior performance compared to previous work.