Supervised Multilabel Image Classification Using Residual Networks with Probabilistic Reasoning
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915620108369920 |
|---|---|
| author | Singh, Lokender Kumar, Saksham Kumar, Chandan |
| author_facet | Singh, Lokender Kumar, Saksham Kumar, Chandan |
| contents | Multilabel image categorization has drawn interest recently because of its numerous computer vision applications. The proposed work introduces a novel method for classifying multilabel images using the COCO-2014 dataset and a modified ResNet-101 architecture. By simulating label dependencies and uncertainties, the approach uses probabilistic reasoning to improve prediction accuracy. Extensive tests show that the model outperforms earlier techniques and approaches to state-of-the-art outcomes in multilabel categorization. The work also thoroughly assesses the model's performance using metrics like precision-recall score and achieves 0.794 mAP on COCO-2014, outperforming ResNet-SRN (0.771) and Vision Transformer baselines (0.785). The novelty of the work lies in integrating probabilistic reasoning into deep learning models to effectively address the challenges presented by multilabel scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_12082 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Supervised Multilabel Image Classification Using Residual Networks with Probabilistic Reasoning Singh, Lokender Kumar, Saksham Kumar, Chandan Computer Vision and Pattern Recognition Multilabel image categorization has drawn interest recently because of its numerous computer vision applications. The proposed work introduces a novel method for classifying multilabel images using the COCO-2014 dataset and a modified ResNet-101 architecture. By simulating label dependencies and uncertainties, the approach uses probabilistic reasoning to improve prediction accuracy. Extensive tests show that the model outperforms earlier techniques and approaches to state-of-the-art outcomes in multilabel categorization. The work also thoroughly assesses the model's performance using metrics like precision-recall score and achieves 0.794 mAP on COCO-2014, outperforming ResNet-SRN (0.771) and Vision Transformer baselines (0.785). The novelty of the work lies in integrating probabilistic reasoning into deep learning models to effectively address the challenges presented by multilabel scenarios. |
| title | Supervised Multilabel Image Classification Using Residual Networks with Probabilistic Reasoning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.12082 |