Asymmetric Feature Maps with Application to Sketch Based Retrieval
This work addresses efficient and accurate sketch-based image retrieval for computer vision applications, with incremental improvements in speed and performance.
The paper tackles sketch-based image retrieval by introducing asymmetric feature maps (AFM) to evaluate multiple kernels efficiently without increasing memory, achieving an order of magnitude speed-up and significantly exceeding state-of-the-art results on standard benchmarks.
We propose a novel concept of asymmetric feature maps (AFM), which allows to evaluate multiple kernels between a query and database entries without increasing the memory requirements. To demonstrate the advantages of the AFM method, we derive a short vector image representation that, due to asymmetric feature maps, supports efficient scale and translation invariant sketch-based image retrieval. Unlike most of the short-code based retrieval systems, the proposed method provides the query localization in the retrieved image. The efficiency of the search is boosted by approximating a 2D translation search via trigonometric polynomial of scores by 1D projections. The projections are a special case of AFM. An order of magnitude speed-up is achieved compared to traditional trigonometric polynomials. The results are boosted by an image-based average query expansion, exceeding significantly the state of the art on standard benchmarks.