Matches in SemOpenAlex for { <https://semopenalex.org/work/W4288356859> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W4288356859 abstract "One of the hallmarks of human intelligence is the ability to compose learned knowledge into novel concepts which can be recognized without a single training example. In contrast, current state-of-the-art methods require hundreds of training examples for each possible category to build reliable and accurate classifiers. To alleviate this striking difference in efficiency, we propose a task-driven modular architecture for compositional reasoning and sample efficient learning. Our architecture consists of a set of neural network modules, which are small fully connected layers operating in semantic concept space. These modules are configured through a gating function conditioned on the task to produce features representing the compatibility between the input image and the concept under consideration. This enables us to express tasks as a combination of sub-tasks and to generalize to unseen categories by reweighting a set of small modules. Furthermore, the network can be trained efficiently as it is fully differentiable and its modules operate on small sub-spaces. We focus our study on the problem of compositional zero-shot classification of object-attribute categories. We show in our experiments that current evaluation metrics are flawed as they only consider unseen object-attribute pairs. When extending the evaluation to the generalized setting which accounts also for pairs seen during training, we discover that naive baseline methods perform similarly or better than current approaches. However, our modular network is able to outperform all existing approaches on two widely-used benchmark datasets." @default.
- W4288356859 created "2022-07-29" @default.
- W4288356859 creator A5000667901 @default.
- W4288356859 creator A5053034244 @default.
- W4288356859 creator A5066334452 @default.
- W4288356859 creator A5077887756 @default.
- W4288356859 date "2019-05-14" @default.
- W4288356859 modified "2023-10-16" @default.
- W4288356859 title "Task-Driven Modular Networks for Zero-Shot Compositional Learning" @default.
- W4288356859 doi "https://doi.org/10.48550/arxiv.1905.05908" @default.
- W4288356859 hasPublicationYear "2019" @default.
- W4288356859 type Work @default.
- W4288356859 citedByCount "0" @default.
- W4288356859 crossrefType "posted-content" @default.
- W4288356859 hasAuthorship W4288356859A5000667901 @default.
- W4288356859 hasAuthorship W4288356859A5053034244 @default.
- W4288356859 hasAuthorship W4288356859A5066334452 @default.
- W4288356859 hasAuthorship W4288356859A5077887756 @default.
- W4288356859 hasBestOaLocation W42883568591 @default.
- W4288356859 hasConcept C101468663 @default.
- W4288356859 hasConcept C111919701 @default.
- W4288356859 hasConcept C119857082 @default.
- W4288356859 hasConcept C13280743 @default.
- W4288356859 hasConcept C134306372 @default.
- W4288356859 hasConcept C154945302 @default.
- W4288356859 hasConcept C162324750 @default.
- W4288356859 hasConcept C175202392 @default.
- W4288356859 hasConcept C177264268 @default.
- W4288356859 hasConcept C185798385 @default.
- W4288356859 hasConcept C187736073 @default.
- W4288356859 hasConcept C199360897 @default.
- W4288356859 hasConcept C202615002 @default.
- W4288356859 hasConcept C205649164 @default.
- W4288356859 hasConcept C2780451532 @default.
- W4288356859 hasConcept C2781121602 @default.
- W4288356859 hasConcept C33923547 @default.
- W4288356859 hasConcept C41008148 @default.
- W4288356859 hasConcept C50644808 @default.
- W4288356859 hasConcept C95623464 @default.
- W4288356859 hasConceptScore W4288356859C101468663 @default.
- W4288356859 hasConceptScore W4288356859C111919701 @default.
- W4288356859 hasConceptScore W4288356859C119857082 @default.
- W4288356859 hasConceptScore W4288356859C13280743 @default.
- W4288356859 hasConceptScore W4288356859C134306372 @default.
- W4288356859 hasConceptScore W4288356859C154945302 @default.
- W4288356859 hasConceptScore W4288356859C162324750 @default.
- W4288356859 hasConceptScore W4288356859C175202392 @default.
- W4288356859 hasConceptScore W4288356859C177264268 @default.
- W4288356859 hasConceptScore W4288356859C185798385 @default.
- W4288356859 hasConceptScore W4288356859C187736073 @default.
- W4288356859 hasConceptScore W4288356859C199360897 @default.
- W4288356859 hasConceptScore W4288356859C202615002 @default.
- W4288356859 hasConceptScore W4288356859C205649164 @default.
- W4288356859 hasConceptScore W4288356859C2780451532 @default.
- W4288356859 hasConceptScore W4288356859C2781121602 @default.
- W4288356859 hasConceptScore W4288356859C33923547 @default.
- W4288356859 hasConceptScore W4288356859C41008148 @default.
- W4288356859 hasConceptScore W4288356859C50644808 @default.
- W4288356859 hasConceptScore W4288356859C95623464 @default.
- W4288356859 hasLocation W42883568591 @default.
- W4288356859 hasOpenAccess W4288356859 @default.
- W4288356859 hasPrimaryLocation W42883568591 @default.
- W4288356859 hasRelatedWork W1539559886 @default.
- W4288356859 hasRelatedWork W2003799049 @default.
- W4288356859 hasRelatedWork W2051536348 @default.
- W4288356859 hasRelatedWork W2151243068 @default.
- W4288356859 hasRelatedWork W2156413426 @default.
- W4288356859 hasRelatedWork W2171477698 @default.
- W4288356859 hasRelatedWork W2376718832 @default.
- W4288356859 hasRelatedWork W2532049082 @default.
- W4288356859 hasRelatedWork W2961085424 @default.
- W4288356859 hasRelatedWork W3041008096 @default.
- W4288356859 isParatext "false" @default.
- W4288356859 isRetracted "false" @default.
- W4288356859 workType "article" @default.