| Full text | |
| Author(s): |
Total Authors: 2
|
| Affiliation: | [1] Univ Sao Paulo, ICMC, Sao Carlos - Brazil
Total Affiliations: 1
|
| Document type: | Journal article |
| Source: | NEURAL COMPUTING & APPLICATIONS; v. 34, n. 6 JAN 2022. |
| Web of Science Citations: | 0 |
| Abstract | |
We investigate visual-semantic representations by combining visual features and semantic attributes to form a compact subspace containing the most relevant properties of each domain. This subspace can better represent image features for recognition tasks and even allow to better interpret results in the light of the nature of semantic attributes, offering a path for explainable learning. Experiments were performed in four benchmark datasets and compared against state-of-the-art algorithms. The method shows to be robust for up to 20% degradation of semantic attributes and offering possibilities for future work on the deployment of an automatic gathering of semantic data to improve representations for image classification. Additionally, empirical evidence suggests the high-level concepts adds linearity to the feature space, allowing for example PCA and SVM to perform well in the combined visual and semantic features. Also, the representations allow for zero-shot learning which demonstrates the viability of merging semantic and visual data at both training and test time for learning aspects that transcend class boundaries that allow the classification of unseen data. (AU) | |
| FAPESP's process: | 18/22482-0 - Learning features from visual content under limited supervision using multiple domains |
| Grantee: | Moacir Antonelli Ponti |
| Support Opportunities: | Regular Research Grants |
| FAPESP's process: | 19/07316-0 - Singularity theory and its applications to differential geometry, differential equations and computer vision |
| Grantee: | Farid Tari |
| Support Opportunities: | Research Projects - Thematic Grants |