Matches in SemOpenAlex for { <https://semopenalex.org/work/W3217245302> ?p ?o ?g. }
Showing items 1 to 69 of
69
with 100 items per page.
- W3217245302 abstract "Learning effective visual representations without human supervision is a long-standing problem in computer vision. Recent advances in self-supervised learning algorithms have utilized contrastive learning, with methods such as SimCLR, which applies a composition of augmentations to an image, and minimizes a contrastive loss between the two augmented images. In this paper, we present CLAWS, an annotation-efficient learning framework, addressing the problem of manually labeling large-scale agricultural datasets along with potential applications such as anomaly detection and plant growth analytics. CLAWS uses a network backbone inspired by SimCLR and weak supervision to investigate the effect of contrastive learning within class clusters. In addition, we inject a hard attention mask to the cropped input image before maximizing agreement between the image pairs using a contrastive loss function. This mask forces the network to focus on pertinent object features and ignore background features. We compare results between a supervised SimCLR and CLAWS using an agricultural dataset with 227,060 samples consisting of 11 different crop classes. Our experiments and extensive evaluations show that CLAWS achieves a competitive NMI score of 0.7325. Furthermore, CLAWS engenders the creation of low dimensional representations of very large datasets with minimal parameter tuning and forming well-defined clusters, which lends themselves to using efficient, transparent, and highly interpretable clustering methods such as Gaussian Mixture Models." @default.
- W3217245302 created "2021-12-06" @default.
- W3217245302 creator A5049427265 @default.
- W3217245302 creator A5051734156 @default.
- W3217245302 creator A5053891870 @default.
- W3217245302 creator A5057733067 @default.
- W3217245302 creator A5079359777 @default.
- W3217245302 date "2021-12-01" @default.
- W3217245302 modified "2023-09-27" @default.
- W3217245302 title "CLAWS: Contrastive Learning with hard Attention and Weak Supervision." @default.
- W3217245302 cites W2006946375 @default.
- W3217245302 cites W2046079134 @default.
- W3217245302 cites W2108384452 @default.
- W3217245302 cites W2842511635 @default.
- W3217245302 cites W2887997457 @default.
- W3217245302 cites W2946948417 @default.
- W3217245302 cites W2948012107 @default.
- W3217245302 cites W2951292523 @default.
- W3217245302 cites W3005680577 @default.
- W3217245302 cites W3035060554 @default.
- W3217245302 cites W3035524453 @default.
- W3217245302 cites W3095121901 @default.
- W3217245302 cites W3171007011 @default.
- W3217245302 cites W3203724306 @default.
- W3217245302 hasPublicationYear "2021" @default.
- W3217245302 type Work @default.
- W3217245302 sameAs 3217245302 @default.
- W3217245302 citedByCount "0" @default.
- W3217245302 crossrefType "posted-content" @default.
- W3217245302 hasAuthorship W3217245302A5049427265 @default.
- W3217245302 hasAuthorship W3217245302A5051734156 @default.
- W3217245302 hasAuthorship W3217245302A5053891870 @default.
- W3217245302 hasAuthorship W3217245302A5057733067 @default.
- W3217245302 hasAuthorship W3217245302A5079359777 @default.
- W3217245302 hasConcept C108583219 @default.
- W3217245302 hasConcept C115961682 @default.
- W3217245302 hasConcept C119857082 @default.
- W3217245302 hasConcept C120665830 @default.
- W3217245302 hasConcept C121332964 @default.
- W3217245302 hasConcept C138885662 @default.
- W3217245302 hasConcept C153180895 @default.
- W3217245302 hasConcept C154945302 @default.
- W3217245302 hasConcept C192209626 @default.
- W3217245302 hasConcept C2776401178 @default.
- W3217245302 hasConcept C2777212361 @default.
- W3217245302 hasConcept C41008148 @default.
- W3217245302 hasConcept C41895202 @default.
- W3217245302 hasConcept C73555534 @default.
- W3217245302 hasConceptScore W3217245302C108583219 @default.
- W3217245302 hasConceptScore W3217245302C115961682 @default.
- W3217245302 hasConceptScore W3217245302C119857082 @default.
- W3217245302 hasConceptScore W3217245302C120665830 @default.
- W3217245302 hasConceptScore W3217245302C121332964 @default.
- W3217245302 hasConceptScore W3217245302C138885662 @default.
- W3217245302 hasConceptScore W3217245302C153180895 @default.
- W3217245302 hasConceptScore W3217245302C154945302 @default.
- W3217245302 hasConceptScore W3217245302C192209626 @default.
- W3217245302 hasConceptScore W3217245302C2776401178 @default.
- W3217245302 hasConceptScore W3217245302C2777212361 @default.
- W3217245302 hasConceptScore W3217245302C41008148 @default.
- W3217245302 hasConceptScore W3217245302C41895202 @default.
- W3217245302 hasConceptScore W3217245302C73555534 @default.
- W3217245302 hasLocation W32172453021 @default.
- W3217245302 hasOpenAccess W3217245302 @default.
- W3217245302 hasPrimaryLocation W32172453021 @default.
- W3217245302 isParatext "false" @default.
- W3217245302 isRetracted "false" @default.
- W3217245302 magId "3217245302" @default.
- W3217245302 workType "article" @default.