Continual Error Correction on Low-Resource Devices
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909926989758464 |
|---|---|
| author | Paramonov, Kirill Ozay, Mete Mystakidis, Aristeidis Tsalikidis, Nikolaos Sotos, Dimitrios Drosou, Anastasios Tzovaras, Dimitrios Kim, Hyunjun Chang, Kiseok Mo, Sangdok Kim, Namwoong Yoo, Woojong Moon, Jijoong Michieli, Umberto |
| author_facet | Paramonov, Kirill Ozay, Mete Mystakidis, Aristeidis Tsalikidis, Nikolaos Sotos, Dimitrios Drosou, Anastasios Tzovaras, Dimitrios Kim, Hyunjun Chang, Kiseok Mo, Sangdok Kim, Namwoong Yoo, Woojong Moon, Jijoong Michieli, Umberto |
| contents | The proliferation of AI models in everyday devices has highlighted a critical challenge: prediction errors that degrade user experience. While existing solutions focus on error detection, they rarely provide efficient correction mechanisms, especially for resource-constrained devices. We present a novel system enabling users to correct AI misclassifications through few-shot learning, requiring minimal computational resources and storage. Our approach combines server-side foundation model training with on-device prototype-based classification, enabling efficient error correction through prototype updates rather than model retraining. The system consists of two key components: (1) a server-side pipeline that leverages knowledge distillation to transfer robust feature representations from foundation models to device-compatible architectures, and (2) a device-side mechanism that enables ultra-efficient error correction through prototype adaptation. We demonstrate our system's effectiveness on both image classification and object detection tasks, achieving over 50% error correction in one-shot scenarios on Food-101 and Flowers-102 datasets while maintaining minimal forgetting (less than 0.02%) and negligible computational overhead. Our implementation, validated through an Android demonstration app, proves the system's practicality in real-world scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_21652 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Continual Error Correction on Low-Resource Devices Paramonov, Kirill Ozay, Mete Mystakidis, Aristeidis Tsalikidis, Nikolaos Sotos, Dimitrios Drosou, Anastasios Tzovaras, Dimitrios Kim, Hyunjun Chang, Kiseok Mo, Sangdok Kim, Namwoong Yoo, Woojong Moon, Jijoong Michieli, Umberto Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning The proliferation of AI models in everyday devices has highlighted a critical challenge: prediction errors that degrade user experience. While existing solutions focus on error detection, they rarely provide efficient correction mechanisms, especially for resource-constrained devices. We present a novel system enabling users to correct AI misclassifications through few-shot learning, requiring minimal computational resources and storage. Our approach combines server-side foundation model training with on-device prototype-based classification, enabling efficient error correction through prototype updates rather than model retraining. The system consists of two key components: (1) a server-side pipeline that leverages knowledge distillation to transfer robust feature representations from foundation models to device-compatible architectures, and (2) a device-side mechanism that enables ultra-efficient error correction through prototype adaptation. We demonstrate our system's effectiveness on both image classification and object detection tasks, achieving over 50% error correction in one-shot scenarios on Food-101 and Flowers-102 datasets while maintaining minimal forgetting (less than 0.02%) and negligible computational overhead. Our implementation, validated through an Android demonstration app, proves the system's practicality in real-world scenarios. |
| title | Continual Error Correction on Low-Resource Devices |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2511.21652 |