Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387623711> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W4387623711 endingPage "14" @default.
- W4387623711 startingPage "1" @default.
- W4387623711 abstract "As a classical feature compression technique, quantization is usually coupled with inverted indices for scalable image retrieval. Most quantization methods explicitly divide feature space into Voronoi cells, and quantize feature vectors in each cell into the centroids learned from data distribution. However, Voronoi decomposition is difficult to achieve discriminative space partition for semantic image retrieval. In this paper, we explore semantic-aware feature space partition by deep neural network instead of Voronoi cells. To this end, we propose a new deep probabilistic quantization method, abbreviated as DeepIndex, which constructs inverted indices without explicit centroid learning. In our method, the deep neural network takes an image as input and outputs its probability of being put into each inverted index list. During training, we progressively quantize each image into the inverted lists with the top- T maximal probabilities, and calculate the reward of each trial based on retrieval accuracy. We optimize the deep neural network to maximize the probability of the inverted list with maximal reward. In this way, the retrieval performance is directly optimized, leading to a more semantically discriminative space partition than other quantization methods. The experiments on public image datasets demonstrate the effectiveness of our DeepIndex method on semantic image retrieval." @default.
- W4387623711 created "2023-10-14" @default.
- W4387623711 creator A5037947792 @default.
- W4387623711 creator A5046805800 @default.
- W4387623711 creator A5049085663 @default.
- W4387623711 creator A5061910607 @default.
- W4387623711 creator A5064753974 @default.
- W4387623711 date "2023-01-01" @default.
- W4387623711 modified "2023-10-15" @default.
- W4387623711 title "Towards Codebook-Free Deep Probabilistic Quantization for Image Retrieval" @default.
- W4387623711 doi "https://doi.org/10.1109/tpami.2023.3324021" @default.
- W4387623711 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37831563" @default.
- W4387623711 hasPublicationYear "2023" @default.
- W4387623711 type Work @default.
- W4387623711 citedByCount "0" @default.
- W4387623711 crossrefType "journal-article" @default.
- W4387623711 hasAuthorship W4387623711A5037947792 @default.
- W4387623711 hasAuthorship W4387623711A5046805800 @default.
- W4387623711 hasAuthorship W4387623711A5049085663 @default.
- W4387623711 hasAuthorship W4387623711A5061910607 @default.
- W4387623711 hasAuthorship W4387623711A5064753974 @default.
- W4387623711 hasConcept C108583219 @default.
- W4387623711 hasConcept C115961682 @default.
- W4387623711 hasConcept C127759330 @default.
- W4387623711 hasConcept C146599234 @default.
- W4387623711 hasConcept C153180895 @default.
- W4387623711 hasConcept C154945302 @default.
- W4387623711 hasConcept C1667742 @default.
- W4387623711 hasConcept C189391414 @default.
- W4387623711 hasConcept C199833920 @default.
- W4387623711 hasConcept C24881265 @default.
- W4387623711 hasConcept C2524010 @default.
- W4387623711 hasConcept C28855332 @default.
- W4387623711 hasConcept C31972630 @default.
- W4387623711 hasConcept C33923547 @default.
- W4387623711 hasConcept C41008148 @default.
- W4387623711 hasConcept C49937458 @default.
- W4387623711 hasConcept C83665646 @default.
- W4387623711 hasConcept C97931131 @default.
- W4387623711 hasConceptScore W4387623711C108583219 @default.
- W4387623711 hasConceptScore W4387623711C115961682 @default.
- W4387623711 hasConceptScore W4387623711C127759330 @default.
- W4387623711 hasConceptScore W4387623711C146599234 @default.
- W4387623711 hasConceptScore W4387623711C153180895 @default.
- W4387623711 hasConceptScore W4387623711C154945302 @default.
- W4387623711 hasConceptScore W4387623711C1667742 @default.
- W4387623711 hasConceptScore W4387623711C189391414 @default.
- W4387623711 hasConceptScore W4387623711C199833920 @default.
- W4387623711 hasConceptScore W4387623711C24881265 @default.
- W4387623711 hasConceptScore W4387623711C2524010 @default.
- W4387623711 hasConceptScore W4387623711C28855332 @default.
- W4387623711 hasConceptScore W4387623711C31972630 @default.
- W4387623711 hasConceptScore W4387623711C33923547 @default.
- W4387623711 hasConceptScore W4387623711C41008148 @default.
- W4387623711 hasConceptScore W4387623711C49937458 @default.
- W4387623711 hasConceptScore W4387623711C83665646 @default.
- W4387623711 hasConceptScore W4387623711C97931131 @default.
- W4387623711 hasLocation W43876237111 @default.
- W4387623711 hasLocation W43876237112 @default.
- W4387623711 hasOpenAccess W4387623711 @default.
- W4387623711 hasPrimaryLocation W43876237111 @default.
- W4387623711 hasRelatedWork W156190883 @default.
- W4387623711 hasRelatedWork W1929869830 @default.
- W4387623711 hasRelatedWork W2017401491 @default.
- W4387623711 hasRelatedWork W2017514583 @default.
- W4387623711 hasRelatedWork W2062765737 @default.
- W4387623711 hasRelatedWork W2100120615 @default.
- W4387623711 hasRelatedWork W2148772884 @default.
- W4387623711 hasRelatedWork W2165855302 @default.
- W4387623711 hasRelatedWork W2352648934 @default.
- W4387623711 hasRelatedWork W2387054321 @default.
- W4387623711 isParatext "false" @default.
- W4387623711 isRetracted "false" @default.
- W4387623711 workType "article" @default.