Hyperspherical Classification with Dynamic Label-to-Prototype Assignment
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913282488532992 |
|---|---|
| author | Saadabadi, Mohammad Saeed Ebrahimi Dabouei, Ali Malakshan, Sahar Rahimi Nasrabad, Nasser M. |
| author_facet | Saadabadi, Mohammad Saeed Ebrahimi Dabouei, Ali Malakshan, Sahar Rahimi Nasrabad, Nasser M. |
| contents | Aiming to enhance the utilization of metric space by the parametric softmax classifier, recent studies suggest replacing it with a non-parametric alternative. Although a non-parametric classifier may provide better metric space utilization, it introduces the challenge of capturing inter-class relationships. A shared characteristic among prior non-parametric classifiers is the static assignment of labels to prototypes during the training, ie, each prototype consistently represents a class throughout the training course. Orthogonal to previous works, we present a simple yet effective method to optimize the category assigned to each prototype (label-to-prototype assignment) during the training. To this aim, we formalize the problem as a two-step optimization objective over network parameters and label-to-prototype assignment mapping. We solve this optimization using a sequential combination of gradient descent and Bipartide matching. We demonstrate the benefits of the proposed approach by conducting experiments on balanced and long-tail classification problems using different backbone network architectures. In particular, our method outperforms its competitors by 1.22\% accuracy on CIFAR-100, and 2.15\% on ImageNet-200 using a metric space dimension half of the size of its competitors. Code: https://github.com/msed-Ebrahimi/DL2PA_CVPR24 |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_16937 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Hyperspherical Classification with Dynamic Label-to-Prototype Assignment Saadabadi, Mohammad Saeed Ebrahimi Dabouei, Ali Malakshan, Sahar Rahimi Nasrabad, Nasser M. Computer Vision and Pattern Recognition Aiming to enhance the utilization of metric space by the parametric softmax classifier, recent studies suggest replacing it with a non-parametric alternative. Although a non-parametric classifier may provide better metric space utilization, it introduces the challenge of capturing inter-class relationships. A shared characteristic among prior non-parametric classifiers is the static assignment of labels to prototypes during the training, ie, each prototype consistently represents a class throughout the training course. Orthogonal to previous works, we present a simple yet effective method to optimize the category assigned to each prototype (label-to-prototype assignment) during the training. To this aim, we formalize the problem as a two-step optimization objective over network parameters and label-to-prototype assignment mapping. We solve this optimization using a sequential combination of gradient descent and Bipartide matching. We demonstrate the benefits of the proposed approach by conducting experiments on balanced and long-tail classification problems using different backbone network architectures. In particular, our method outperforms its competitors by 1.22\% accuracy on CIFAR-100, and 2.15\% on ImageNet-200 using a metric space dimension half of the size of its competitors. Code: https://github.com/msed-Ebrahimi/DL2PA_CVPR24 |
| title | Hyperspherical Classification with Dynamic Label-to-Prototype Assignment |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.16937 |