Matches in SemOpenAlex for { <https://semopenalex.org/work/W2904808113> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W2904808113 abstract "For tasks involving language and vision, the current state-of-the-art methods tend not to leverage any additional information that might be present to gather relevant (commonsense) knowledge. A representative task is Visual Question Answering where large diagnostic datasets have been proposed to test a system's capability of answering questions about images. The training data is often accompanied by annotations of individual object properties and spatial locations. In this work, we take a step towards integrating this additional privileged information in the form of spatial knowledge to aid in visual reasoning. We propose a framework that combines recent advances in knowledge distillation (teacher-student framework), relational reasoning and probabilistic logical languages to incorporate such knowledge in existing neural networks for the task of Visual Question Answering. Specifically, for a question posed against an image, we use a probabilistic logical language to encode the spatial knowledge and the spatial understanding about the question in the form of a mask that is directly provided to the teacher network. The student network learns from the ground-truth information as well as the teachers prediction via distillation. We also demonstrate the impact of predicting such a mask inside the teachers network using attention. Empirically, we show that both the methods improve the test accuracy over a state-of-the-art approach on a publicly available dataset." @default.
- W2904808113 created "2018-12-22" @default.
- W2904808113 creator A5002278578 @default.
- W2904808113 creator A5015328403 @default.
- W2904808113 creator A5071844229 @default.
- W2904808113 creator A5083735830 @default.
- W2904808113 date "2018-12-10" @default.
- W2904808113 modified "2023-09-27" @default.
- W2904808113 title "Spatial Knowledge Distillation to aid Visual Reasoning" @default.
- W2904808113 cites W1508977358 @default.
- W2904808113 cites W2561715562 @default.
- W2904808113 hasPublicationYear "2018" @default.
- W2904808113 type Work @default.
- W2904808113 sameAs 2904808113 @default.
- W2904808113 citedByCount "0" @default.
- W2904808113 crossrefType "posted-content" @default.
- W2904808113 hasAuthorship W2904808113A5002278578 @default.
- W2904808113 hasAuthorship W2904808113A5015328403 @default.
- W2904808113 hasAuthorship W2904808113A5071844229 @default.
- W2904808113 hasAuthorship W2904808113A5083735830 @default.
- W2904808113 hasConcept C119857082 @default.
- W2904808113 hasConcept C153083717 @default.
- W2904808113 hasConcept C154945302 @default.
- W2904808113 hasConcept C155911833 @default.
- W2904808113 hasConcept C161301231 @default.
- W2904808113 hasConcept C162324750 @default.
- W2904808113 hasConcept C187736073 @default.
- W2904808113 hasConcept C193221554 @default.
- W2904808113 hasConcept C204321447 @default.
- W2904808113 hasConcept C2777508537 @default.
- W2904808113 hasConcept C2780451532 @default.
- W2904808113 hasConcept C30542707 @default.
- W2904808113 hasConcept C41008148 @default.
- W2904808113 hasConcept C44291984 @default.
- W2904808113 hasConcept C49937458 @default.
- W2904808113 hasConceptScore W2904808113C119857082 @default.
- W2904808113 hasConceptScore W2904808113C153083717 @default.
- W2904808113 hasConceptScore W2904808113C154945302 @default.
- W2904808113 hasConceptScore W2904808113C155911833 @default.
- W2904808113 hasConceptScore W2904808113C161301231 @default.
- W2904808113 hasConceptScore W2904808113C162324750 @default.
- W2904808113 hasConceptScore W2904808113C187736073 @default.
- W2904808113 hasConceptScore W2904808113C193221554 @default.
- W2904808113 hasConceptScore W2904808113C204321447 @default.
- W2904808113 hasConceptScore W2904808113C2777508537 @default.
- W2904808113 hasConceptScore W2904808113C2780451532 @default.
- W2904808113 hasConceptScore W2904808113C30542707 @default.
- W2904808113 hasConceptScore W2904808113C41008148 @default.
- W2904808113 hasConceptScore W2904808113C44291984 @default.
- W2904808113 hasConceptScore W2904808113C49937458 @default.
- W2904808113 hasLocation W29048081131 @default.
- W2904808113 hasOpenAccess W2904808113 @default.
- W2904808113 hasPrimaryLocation W29048081131 @default.
- W2904808113 hasRelatedWork W118961843 @default.
- W2904808113 hasRelatedWork W1980221247 @default.
- W2904808113 hasRelatedWork W2770545708 @default.
- W2904808113 hasRelatedWork W2899795261 @default.
- W2904808113 hasRelatedWork W2953212746 @default.
- W2904808113 hasRelatedWork W2963518342 @default.
- W2904808113 hasRelatedWork W2963758505 @default.
- W2904808113 hasRelatedWork W2964092725 @default.
- W2904808113 hasRelatedWork W2965527197 @default.
- W2904808113 hasRelatedWork W3021007069 @default.
- W2904808113 hasRelatedWork W3034209796 @default.
- W2904808113 hasRelatedWork W3036226265 @default.
- W2904808113 hasRelatedWork W3082938327 @default.
- W2904808113 hasRelatedWork W3156472912 @default.
- W2904808113 hasRelatedWork W3167150513 @default.
- W2904808113 hasRelatedWork W3177445028 @default.
- W2904808113 hasRelatedWork W3186479087 @default.
- W2904808113 hasRelatedWork W3193268468 @default.
- W2904808113 hasRelatedWork W3199088499 @default.
- W2904808113 hasRelatedWork W3200057130 @default.
- W2904808113 isParatext "false" @default.
- W2904808113 isRetracted "false" @default.
- W2904808113 magId "2904808113" @default.
- W2904808113 workType "article" @default.