Semi-Supervised Exploration in Image Retrieval
This work addresses landmark image retrieval for computer vision applications, but it appears incremental as it builds on existing graph traversal methods.
The authors tackled the Landmark Image Retrieval Challenge 2019 by combining global and local models to create an initial KNN graph and refining it with a novel semi-supervised extension of EGT, resulting in improved candidate retrieval.
We present our solution to Landmark Image Retrieval Challenge 2019. This challenge was based on the large Google Landmarks Dataset V2[9]. The goal was to retrieve all database images containing the same landmark for every provided query image. Our solution is a combination of global and local models to form an initial KNN graph. We then use a novel extension of the recently proposed graph traversal method EGT [1] referred to as semi-supervised EGT to refine the graph and retrieve better candidates.