Matches in SemOpenAlex for { <https://semopenalex.org/work/W4310486995> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W4310486995 abstract "This paper presents a grounded language-image pre-training (GLIP) model for learning object-level, language-aware, and semantic-rich visual representations. GLIP unifies object detection and phrase grounding for pre-training. The unification brings two benefits: 1) it allows GLIP to learn from both detection and grounding data to improve both tasks and bootstrap a good grounding model; 2) GLIP can leverage massive image-text pairs by generating grounding boxes in a self-training fashion, making the learned representation semantic-rich. In our experiments, we pre-train GLIP on 27M grounding data, including 3M human-annotated and 24M web-crawled image-text pairs. The learned representations demonstrate strong zero-shot and few-shot transferability to various object-level recognition tasks. 1) When directly evaluated on COCO and LVIS (without seeing any images in COCO during pre-training), GLIP achieves 49.8 AP and 26.9 AP, respectively, surpassing many supervised baselines. 2) After fine-tuned on COCO, GLIP achieves 60.8 AP on val and 61.5 AP on test-dev, surpassing prior SoTA. 3) When transferred to 13 downstream object detection tasks, a 1-shot GLIP rivals with a fully-supervised Dynamic Head. Code is released at https://github.com/microsoft/GLIP." @default.
- W4310486995 created "2022-12-11" @default.
- W4310486995 creator A5003075563 @default.
- W4310486995 creator A5004824034 @default.
- W4310486995 creator A5016456840 @default.
- W4310486995 creator A5040199499 @default.
- W4310486995 creator A5044591447 @default.
- W4310486995 creator A5046214153 @default.
- W4310486995 creator A5046887099 @default.
- W4310486995 creator A5047233371 @default.
- W4310486995 creator A5059735251 @default.
- W4310486995 creator A5071798264 @default.
- W4310486995 creator A5073435344 @default.
- W4310486995 creator A5087096372 @default.
- W4310486995 date "2021-12-07" @default.
- W4310486995 modified "2023-10-18" @default.
- W4310486995 title "Grounded Language-Image Pre-training" @default.
- W4310486995 doi "https://doi.org/10.48550/arxiv.2112.03857" @default.
- W4310486995 hasPublicationYear "2021" @default.
- W4310486995 type Work @default.
- W4310486995 citedByCount "0" @default.
- W4310486995 crossrefType "posted-content" @default.
- W4310486995 hasAuthorship W4310486995A5003075563 @default.
- W4310486995 hasAuthorship W4310486995A5004824034 @default.
- W4310486995 hasAuthorship W4310486995A5016456840 @default.
- W4310486995 hasAuthorship W4310486995A5040199499 @default.
- W4310486995 hasAuthorship W4310486995A5044591447 @default.
- W4310486995 hasAuthorship W4310486995A5046214153 @default.
- W4310486995 hasAuthorship W4310486995A5046887099 @default.
- W4310486995 hasAuthorship W4310486995A5047233371 @default.
- W4310486995 hasAuthorship W4310486995A5059735251 @default.
- W4310486995 hasAuthorship W4310486995A5071798264 @default.
- W4310486995 hasAuthorship W4310486995A5073435344 @default.
- W4310486995 hasAuthorship W4310486995A5087096372 @default.
- W4310486995 hasBestOaLocation W43104869951 @default.
- W4310486995 hasConcept C115961682 @default.
- W4310486995 hasConcept C119857082 @default.
- W4310486995 hasConcept C153083717 @default.
- W4310486995 hasConcept C153180895 @default.
- W4310486995 hasConcept C154945302 @default.
- W4310486995 hasConcept C178790620 @default.
- W4310486995 hasConcept C185592680 @default.
- W4310486995 hasConcept C204321447 @default.
- W4310486995 hasConcept C2776151529 @default.
- W4310486995 hasConcept C2776224158 @default.
- W4310486995 hasConcept C2778344882 @default.
- W4310486995 hasConcept C2781238097 @default.
- W4310486995 hasConcept C41008148 @default.
- W4310486995 hasConcept C51632099 @default.
- W4310486995 hasConceptScore W4310486995C115961682 @default.
- W4310486995 hasConceptScore W4310486995C119857082 @default.
- W4310486995 hasConceptScore W4310486995C153083717 @default.
- W4310486995 hasConceptScore W4310486995C153180895 @default.
- W4310486995 hasConceptScore W4310486995C154945302 @default.
- W4310486995 hasConceptScore W4310486995C178790620 @default.
- W4310486995 hasConceptScore W4310486995C185592680 @default.
- W4310486995 hasConceptScore W4310486995C204321447 @default.
- W4310486995 hasConceptScore W4310486995C2776151529 @default.
- W4310486995 hasConceptScore W4310486995C2776224158 @default.
- W4310486995 hasConceptScore W4310486995C2778344882 @default.
- W4310486995 hasConceptScore W4310486995C2781238097 @default.
- W4310486995 hasConceptScore W4310486995C41008148 @default.
- W4310486995 hasConceptScore W4310486995C51632099 @default.
- W4310486995 hasLocation W43104869951 @default.
- W4310486995 hasLocation W43104869952 @default.
- W4310486995 hasOpenAccess W4310486995 @default.
- W4310486995 hasPrimaryLocation W43104869951 @default.
- W4310486995 hasRelatedWork W1988485990 @default.
- W4310486995 hasRelatedWork W2095705906 @default.
- W4310486995 hasRelatedWork W2127769904 @default.
- W4310486995 hasRelatedWork W2369308426 @default.
- W4310486995 hasRelatedWork W2732308154 @default.
- W4310486995 hasRelatedWork W2801801420 @default.
- W4310486995 hasRelatedWork W2807284393 @default.
- W4310486995 hasRelatedWork W2970686063 @default.
- W4310486995 hasRelatedWork W2975200075 @default.
- W4310486995 hasRelatedWork W3187859696 @default.
- W4310486995 isParatext "false" @default.
- W4310486995 isRetracted "false" @default.
- W4310486995 workType "article" @default.