Efficient Diffusion on Region Manifolds: Recovering Small Objects with Compact CNN Representations
This addresses a common failure case in CNN-based image retrieval for small objects, offering an incremental improvement over existing diffusion methods.
The paper tackles the problem of small object retrieval in image search by performing diffusion on overlapping region descriptors instead of global image features, achieving significant performance improvements on standard benchmarks with query times under one second.
Query expansion is a popular method to improve the quality of image retrieval with both conventional and CNN representations. It has been so far limited to global image similarity. This work focuses on diffusion, a mechanism that captures the image manifold in the feature space. The diffusion is carried out on descriptors of overlapping image regions rather than on a global image descriptor like in previous approaches. An efficient off-line stage allows optional reduction in the number of stored regions. In the on-line stage, the proposed handling of unseen queries in the indexing stage removes additional computation to adjust the precomputed data. We perform diffusion through a sparse linear system solver, yielding practical query times well below one second. Experimentally, we observe a significant boost in performance of image retrieval with compact CNN descriptors on standard benchmarks, especially when the query object covers only a small part of the image. Small objects have been a common failure case of CNN-based retrieval.