Matches in SemOpenAlex for { <https://semopenalex.org/work/W4226514220> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W4226514220 abstract "Fine-grained image classification is a challenging computer vision task where various species share similar visual appearances, resulting in misclassification if merely based on visual clues. Therefore, it is helpful to leverage additional information, e.g., the locations and dates for data shooting, which can be easily accessible but rarely exploited. In this paper, we first demonstrate that existing multimodal methods fuse multiple features only on a single dimension, which essentially has insufficient help in feature discrimination. To fully explore the potential of multimodal information, we propose a dynamic MLP on top of the image representation, which interacts with multimodal features at a higher and broader dimension. The dynamic MLP is an efficient structure parameterized by the learned embeddings of variable locations and dates. It can be regarded as an adaptive nonlinear projection for generating more discriminative image representations in visual tasks. To our best knowledge, it is the first attempt to explore the idea of dynamic networks to exploit multimodal information in fine-grained image classification tasks. Extensive experiments demonstrate the effectiveness of our method. The t-SNE algorithm visually indicates that our technique improves the recognizability of image representations that are visually similar but with different categories. Furthermore, among published works across multiple fine-grained datasets, dynamic MLP consistently achieves SOTA results https://paperswithcode.com/dataset/inaturalist and takes third place in the iNaturalist challenge at FGVC8 https://www.kaggle.com/c/inaturalist-2021/leaderboard. Code is available at https://github.com/ylingfeng/DynamicMLP.git" @default.
- W4226514220 created "2022-05-05" @default.
- W4226514220 creator A5002416341 @default.
- W4226514220 creator A5009232538 @default.
- W4226514220 creator A5017320345 @default.
- W4226514220 creator A5035488063 @default.
- W4226514220 creator A5037317830 @default.
- W4226514220 creator A5040859980 @default.
- W4226514220 creator A5055782213 @default.
- W4226514220 creator A5070740938 @default.
- W4226514220 date "2022-03-07" @default.
- W4226514220 modified "2023-09-27" @default.
- W4226514220 title "Dynamic MLP for Fine-Grained Image Classification by Leveraging Geographical and Temporal Information" @default.
- W4226514220 doi "https://doi.org/10.48550/arxiv.2203.03253" @default.
- W4226514220 hasPublicationYear "2022" @default.
- W4226514220 type Work @default.
- W4226514220 citedByCount "0" @default.
- W4226514220 crossrefType "posted-content" @default.
- W4226514220 hasAuthorship W4226514220A5002416341 @default.
- W4226514220 hasAuthorship W4226514220A5009232538 @default.
- W4226514220 hasAuthorship W4226514220A5017320345 @default.
- W4226514220 hasAuthorship W4226514220A5035488063 @default.
- W4226514220 hasAuthorship W4226514220A5037317830 @default.
- W4226514220 hasAuthorship W4226514220A5040859980 @default.
- W4226514220 hasAuthorship W4226514220A5055782213 @default.
- W4226514220 hasAuthorship W4226514220A5070740938 @default.
- W4226514220 hasBestOaLocation W42265142201 @default.
- W4226514220 hasConcept C11413529 @default.
- W4226514220 hasConcept C115961682 @default.
- W4226514220 hasConcept C119857082 @default.
- W4226514220 hasConcept C138885662 @default.
- W4226514220 hasConcept C153083717 @default.
- W4226514220 hasConcept C153180895 @default.
- W4226514220 hasConcept C154945302 @default.
- W4226514220 hasConcept C165464430 @default.
- W4226514220 hasConcept C165696696 @default.
- W4226514220 hasConcept C177264268 @default.
- W4226514220 hasConcept C199360897 @default.
- W4226514220 hasConcept C2776401178 @default.
- W4226514220 hasConcept C2776760102 @default.
- W4226514220 hasConcept C38652104 @default.
- W4226514220 hasConcept C41008148 @default.
- W4226514220 hasConcept C41895202 @default.
- W4226514220 hasConcept C97931131 @default.
- W4226514220 hasConceptScore W4226514220C11413529 @default.
- W4226514220 hasConceptScore W4226514220C115961682 @default.
- W4226514220 hasConceptScore W4226514220C119857082 @default.
- W4226514220 hasConceptScore W4226514220C138885662 @default.
- W4226514220 hasConceptScore W4226514220C153083717 @default.
- W4226514220 hasConceptScore W4226514220C153180895 @default.
- W4226514220 hasConceptScore W4226514220C154945302 @default.
- W4226514220 hasConceptScore W4226514220C165464430 @default.
- W4226514220 hasConceptScore W4226514220C165696696 @default.
- W4226514220 hasConceptScore W4226514220C177264268 @default.
- W4226514220 hasConceptScore W4226514220C199360897 @default.
- W4226514220 hasConceptScore W4226514220C2776401178 @default.
- W4226514220 hasConceptScore W4226514220C2776760102 @default.
- W4226514220 hasConceptScore W4226514220C38652104 @default.
- W4226514220 hasConceptScore W4226514220C41008148 @default.
- W4226514220 hasConceptScore W4226514220C41895202 @default.
- W4226514220 hasConceptScore W4226514220C97931131 @default.
- W4226514220 hasLocation W42265142201 @default.
- W4226514220 hasOpenAccess W4226514220 @default.
- W4226514220 hasPrimaryLocation W42265142201 @default.
- W4226514220 hasRelatedWork W1652783584 @default.
- W4226514220 hasRelatedWork W1971623867 @default.
- W4226514220 hasRelatedWork W1982770690 @default.
- W4226514220 hasRelatedWork W1990254706 @default.
- W4226514220 hasRelatedWork W2024160000 @default.
- W4226514220 hasRelatedWork W2404514746 @default.
- W4226514220 hasRelatedWork W2743258233 @default.
- W4226514220 hasRelatedWork W2773500201 @default.
- W4226514220 hasRelatedWork W3013138473 @default.
- W4226514220 hasRelatedWork W4287995534 @default.
- W4226514220 isParatext "false" @default.
- W4226514220 isRetracted "false" @default.
- W4226514220 workType "article" @default.