Matches in SemOpenAlex for { <https://semopenalex.org/work/W4297776992> ?p ?o ?g. }
Showing items 1 to 51 of
51
with 100 items per page.
- W4297776992 abstract "The goal of this work is to efficiently identify visually similar patterns in images, e.g. identifying an artwork detail copied between an engraving and an oil painting, or recognizing parts of a night-time photograph visible in its daytime counterpart. Lack of training data is a key challenge for this co-segmentation task. We present a simple yet surprisingly effective approach to overcome this difficulty: we generate synthetic training pairs by selecting segments in an image and copy-pasting them into another image. We then learn to predict the repeated region masks. We find that it is crucial to predict the correspondences as an auxiliary task and to use Poisson blending and style transfer on the training pairs to generalize on real data. We analyse results with two deep architectures relevant to our joint image analysis task: a transformer-based architecture and Sparse Nc-Net, a recent network designed to predict coarse correspondences using 4D convolutions. We show our approach provides clear improvements for artwork details retrieval on the Brueghel dataset and achieves competitive performance on two place recognition benchmarks, Tokyo247 and Pitts30K. We also demonstrate the potential of our approach for unsupervised image collection analysis by introducing a spectral graph clustering approach to object discovery and demonstrating it on the object discovery dataset of cite{rubinstein2013unsupervised} and the Brueghel dataset. Our code and data are available at http://imagine.enpc.fr/~shenx/SegSwap/." @default.
- W4297776992 created "2022-10-01" @default.
- W4297776992 creator A5012435102 @default.
- W4297776992 creator A5041693326 @default.
- W4297776992 creator A5061634216 @default.
- W4297776992 creator A5077436220 @default.
- W4297776992 date "2021-10-29" @default.
- W4297776992 modified "2023-09-30" @default.
- W4297776992 title "Learning Co-segmentation by Segment Swapping for Retrieval and Discovery" @default.
- W4297776992 doi "https://doi.org/10.48550/arxiv.2110.15904" @default.
- W4297776992 hasPublicationYear "2021" @default.
- W4297776992 type Work @default.
- W4297776992 citedByCount "0" @default.
- W4297776992 crossrefType "posted-content" @default.
- W4297776992 hasAuthorship W4297776992A5012435102 @default.
- W4297776992 hasAuthorship W4297776992A5041693326 @default.
- W4297776992 hasAuthorship W4297776992A5061634216 @default.
- W4297776992 hasAuthorship W4297776992A5077436220 @default.
- W4297776992 hasBestOaLocation W42977769921 @default.
- W4297776992 hasConcept C153180895 @default.
- W4297776992 hasConcept C154945302 @default.
- W4297776992 hasConcept C162324750 @default.
- W4297776992 hasConcept C187736073 @default.
- W4297776992 hasConcept C2780451532 @default.
- W4297776992 hasConcept C41008148 @default.
- W4297776992 hasConcept C73555534 @default.
- W4297776992 hasConcept C89600930 @default.
- W4297776992 hasConceptScore W4297776992C153180895 @default.
- W4297776992 hasConceptScore W4297776992C154945302 @default.
- W4297776992 hasConceptScore W4297776992C162324750 @default.
- W4297776992 hasConceptScore W4297776992C187736073 @default.
- W4297776992 hasConceptScore W4297776992C2780451532 @default.
- W4297776992 hasConceptScore W4297776992C41008148 @default.
- W4297776992 hasConceptScore W4297776992C73555534 @default.
- W4297776992 hasConceptScore W4297776992C89600930 @default.
- W4297776992 hasLocation W42977769921 @default.
- W4297776992 hasOpenAccess W4297776992 @default.
- W4297776992 hasPrimaryLocation W42977769921 @default.
- W4297776992 hasRelatedWork W1507687735 @default.
- W4297776992 hasRelatedWork W2005476934 @default.
- W4297776992 hasRelatedWork W2061502286 @default.
- W4297776992 hasRelatedWork W2510758617 @default.
- W4297776992 hasRelatedWork W2753174232 @default.
- W4297776992 hasRelatedWork W2754350655 @default.
- W4297776992 hasRelatedWork W2897195263 @default.
- W4297776992 hasRelatedWork W3095523211 @default.
- W4297776992 hasRelatedWork W4206076898 @default.
- W4297776992 hasRelatedWork W4226401448 @default.
- W4297776992 isParatext "false" @default.
- W4297776992 isRetracted "false" @default.
- W4297776992 workType "article" @default.