FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2933502442> ?p ?o ?g. }

• W2933502442 abstract "This paper studies the unsupervised embedding learning problem, which requires an effective similarity measurement between samples in low-dimensional embedding space. Motivated by the positive concentrated and negative separated properties observed from category-wise supervised learning, we propose to utilize the instance-wise supervision to approximate these properties, which aims at learning data augmentation invariant and instance spread-out features. To achieve this goal, we propose a novel instance based softmax embedding method, which directly optimizes the `real' instance features on top of the softmax function. It achieves significantly faster learning speed and higher accuracy than all existing methods. The proposed method performs well for both seen and unseen testing categories with cosine similarity. It also achieves competitive performance even without pre-trained network over samples from fine-grained categories." @default.
• W2933502442 created "2019-04-11" @default.
• W2933502442 creator A5008999954 @default.
• W2933502442 creator A5037340457 @default.
• W2933502442 creator A5073568638 @default.
• W2933502442 creator A5079920605 @default.
• W2933502442 date "2019-04-06" @default.
• W2933502442 modified "2023-09-23" @default.
• W2933502442 title "Unsupervised Embedding Learning via Invariant and Spreading Instance Feature" @default.
• W2933502442 cites W1514928307 @default.
• W2933502442 cites W1520997877 @default.
• W2933502442 cites W1532325895 @default.
• W2933502442 cites W1573897183 @default.
• W2933502442 cites W1677182931 @default.
• W2933502442 cites W1797268635 @default.
• W2933502442 cites W1821462560 @default.
• W2933502442 cites W2025768430 @default.
• W2933502442 cites W2054814877 @default.
• W2933502442 cites W2097117768 @default.
• W2933502442 cites W2099471712 @default.
• W2933502442 cites W2106869737 @default.
• W2933502442 cites W2111440402 @default.
• W2933502442 cites W2118858186 @default.
• W2933502442 cites W2130325614 @default.
• W2933502442 cites W2138011018 @default.
• W2933502442 cites W2138621090 @default.
• W2933502442 cites W2139427956 @default.
• W2933502442 cites W2144796873 @default.
• W2933502442 cites W2148349024 @default.
• W2933502442 cites W2161627023 @default.
• W2933502442 cites W219040644 @default.
• W2933502442 cites W2194775991 @default.
• W2933502442 cites W2321533354 @default.
• W2933502442 cites W2326925005 @default.
• W2933502442 cites W2342611082 @default.
• W2933502442 cites W2411541852 @default.
• W2933502442 cites W2412320034 @default.
• W2933502442 cites W2518754566 @default.
• W2933502442 cites W2519998487 @default.
• W2933502442 cites W2520774990 @default.
• W2933502442 cites W2560977758 @default.
• W2933502442 cites W2598634450 @default.
• W2933502442 cites W2603142085 @default.
• W2933502442 cites W2605102252 @default.
• W2933502442 cites W2606611007 @default.
• W2933502442 cites W2613997951 @default.
• W2933502442 cites W2769346661 @default.
• W2933502442 cites W2780186312 @default.
• W2933502442 cites W2798991696 @default.
• W2933502442 cites W2883725317 @default.
• W2933502442 cites W2895589658 @default.
• W2933502442 cites W2962708773 @default.
• W2933502442 cites W2963026686 @default.
• W2933502442 cites W2963350250 @default.
• W2933502442 cites W2963420272 @default.
• W2933502442 cites W2963740830 @default.
• W2933502442 cites W2963989829 @default.
• W2933502442 cites W3118608800 @default.
• W2933502442 cites W343636949 @default.
• W2933502442 cites W630242894 @default.
• W2933502442 doi "https://doi.org/10.48550/arxiv.1904.03436" @default.
• W2933502442 hasPublicationYear "2019" @default.
• W2933502442 type Work @default.
• W2933502442 sameAs 2933502442 @default.
• W2933502442 citedByCount "25" @default.
• W2933502442 countsByYear W29335024422019 @default.
• W2933502442 countsByYear W29335024422020 @default.
• W2933502442 countsByYear W29335024422021 @default.
• W2933502442 crossrefType "posted-content" @default.
• W2933502442 hasAuthorship W2933502442A5008999954 @default.
• W2933502442 hasAuthorship W2933502442A5037340457 @default.
• W2933502442 hasAuthorship W2933502442A5073568638 @default.
• W2933502442 hasAuthorship W2933502442A5079920605 @default.
• W2933502442 hasBestOaLocation W29335024421 @default.
• W2933502442 hasConcept C103278499 @default.
• W2933502442 hasConcept C108583219 @default.
• W2933502442 hasConcept C115961682 @default.
• W2933502442 hasConcept C119857082 @default.
• W2933502442 hasConcept C120822770 @default.
• W2933502442 hasConcept C138885662 @default.
• W2933502442 hasConcept C153180895 @default.
• W2933502442 hasConcept C154945302 @default.
• W2933502442 hasConcept C178009071 @default.
• W2933502442 hasConcept C188441871 @default.
• W2933502442 hasConcept C190470478 @default.
• W2933502442 hasConcept C2524010 @default.
• W2933502442 hasConcept C2776401178 @default.
• W2933502442 hasConcept C33923547 @default.
• W2933502442 hasConcept C37914503 @default.
• W2933502442 hasConcept C41008148 @default.
• W2933502442 hasConcept C41608201 @default.
• W2933502442 hasConcept C41895202 @default.
• W2933502442 hasConcept C59404180 @default.
• W2933502442 hasConcept C8038995 @default.
• W2933502442 hasConcept C83665646 @default.
• W2933502442 hasConceptScore W2933502442C103278499 @default.
• W2933502442 hasConceptScore W2933502442C108583219 @default.
• W2933502442 hasConceptScore W2933502442C115961682 @default.
• W2933502442 hasConceptScore W2933502442C119857082 @default.
• W2933502442 hasConceptScore W2933502442C120822770 @default.

• next