Efficient Diffusion On Region Manifolds: Recovering Small Objects With Compact CNN Representations
2016 · Ahmet Iscen, Giorgos Tolias, Yannis Avrithis, et al.
Abstract
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
Authors
(none)
Tags
Stats
Related papers
- An Efficient Approximate Knn Graph Method For Diffusion On Image Retrieval (2019)6.34
- Efficient Image Retrieval Via Decoupling Diffusion Into Online And Offline Processing (2018)12.25
- Bloom Filters And Compact Hash Codes For Efficient And Distributed Image Retrieval (2016)6.34
- Hybrid Diffusion: Spectral-temporal Graph Filtering For Manifold Ranking (2018)2.26
- From Selective Deep Convolutional Features To Compact Binary Representations For Image Retrieval (2018)10.35
- Accurate And Fast Pixel Retrieval With Spatial And Uncertainty Aware Hypergraph Diffusion (2024)0.00
- Deepdiffusion: Unsupervised Learning Of Retrieval-adapted Representations Via Diffusion-based Ranking On Latent Feature Manifold (2021)5.13
- Context Aware Query Image Representation For Particular Object Retrieval (2017)11.49