Self-Supervised Learning Based Handwriting Verification
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916342056091648 |
|---|---|
| author | Chauhan, Mihir Hashemi, Mohammad Abuzar Satbhai, Abhishek Ali, Mir Basheer Ramamurthy, Bina Gao, Mingchen Lyu, Siwei Srihari, Sargur |
| author_facet | Chauhan, Mihir Hashemi, Mohammad Abuzar Satbhai, Abhishek Ali, Mir Basheer Ramamurthy, Bina Gao, Mingchen Lyu, Siwei Srihari, Sargur |
| contents | We present SSL-HV: Self-Supervised Learning approaches applied to the task of Handwriting Verification. This task involves determining whether a given pair of handwritten images originate from the same or different writer distribution. We have compared the performance of multiple generative, contrastive SSL approaches against handcrafted feature extractors and supervised learning on CEDAR AND dataset. We show that ResNet based Variational Auto-Encoder (VAE) outperforms other generative approaches achieving 76.3% accuracy, while ResNet-18 fine-tuned using Variance-Invariance-Covariance Regularization (VICReg) outperforms other contrastive approaches achieving 78% accuracy. Using a pre-trained VAE and VICReg for the downstream task of writer verification we observed a relative improvement in accuracy of 6.7% and 9% over ResNet-18 supervised baseline with 10% writer labels. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_18320 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Self-Supervised Learning Based Handwriting Verification Chauhan, Mihir Hashemi, Mohammad Abuzar Satbhai, Abhishek Ali, Mir Basheer Ramamurthy, Bina Gao, Mingchen Lyu, Siwei Srihari, Sargur Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language We present SSL-HV: Self-Supervised Learning approaches applied to the task of Handwriting Verification. This task involves determining whether a given pair of handwritten images originate from the same or different writer distribution. We have compared the performance of multiple generative, contrastive SSL approaches against handcrafted feature extractors and supervised learning on CEDAR AND dataset. We show that ResNet based Variational Auto-Encoder (VAE) outperforms other generative approaches achieving 76.3% accuracy, while ResNet-18 fine-tuned using Variance-Invariance-Covariance Regularization (VICReg) outperforms other contrastive approaches achieving 78% accuracy. Using a pre-trained VAE and VICReg for the downstream task of writer verification we observed a relative improvement in accuracy of 6.7% and 9% over ResNet-18 supervised baseline with 10% writer labels. |
| title | Self-Supervised Learning Based Handwriting Verification |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2405.18320 |