Leveraging Implicit Spatial Information in Global Features for Image Retrieval
This work addresses the limitation of spatial information loss in image retrieval, which is crucial for applications like visual search, but it appears incremental as it builds on existing tensor frameworks.
The paper tackled the problem of lost spatial information in global features for image retrieval by integrating relative spatial information into the aggregation process, achieving state-of-the-art performance on datasets like Holidays, Oxford5k, and Paris6k.
Most image retrieval methods use global features that aggregate local distinctive patterns into a single representation. However, the aggregation process destroys the relative spatial information by considering orderless sets of local descriptors. We propose to integrate relative spatial information into the aggregation process by taking into account co-occurrences of local patterns in a tensor framework. The resulting signature called Improved Spatial Tensor Aggregation (ISTA) is able to reach state of the art performances on well known datasets such as Holidays, Oxford5k and Paris6k.