FilterLoss: A Transfer Learning Approach for Communication Scene Recognition
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915784414986240 |
|---|---|
| author | Han, Jiasong Feng, Yufei Zhong, Xiaofeng |
| author_facet | Han, Jiasong Feng, Yufei Zhong, Xiaofeng |
| contents | Communication scene recognition has been widely applied in practice, but using deep learning to address this problem faces challenges such as insufficient data and imbalanced data distribution. To address this, we designed a weighted loss function structure, named FilterLoss, which assigns different loss function weights to different sample points. This allows the deep learning model to focus primarily on high-value samples while appropriately accounting for noisy, boundary-level data points. Additionally, we developed a matching weight filtering algorithm that evaluates the quality of sample points in the input dataset and assigns different weight values to samples based on their quality. By applying this method, when using transfer learning on a highly imbalanced new dataset, the accuracy of the transferred model was restored to 92.34% of the original model's performance. Our experiments also revealed that using this loss function structure allowed the model to maintain good stability despite insufficient and imbalanced data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_07772 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | FilterLoss: A Transfer Learning Approach for Communication Scene Recognition Han, Jiasong Feng, Yufei Zhong, Xiaofeng Econometrics Communication scene recognition has been widely applied in practice, but using deep learning to address this problem faces challenges such as insufficient data and imbalanced data distribution. To address this, we designed a weighted loss function structure, named FilterLoss, which assigns different loss function weights to different sample points. This allows the deep learning model to focus primarily on high-value samples while appropriately accounting for noisy, boundary-level data points. Additionally, we developed a matching weight filtering algorithm that evaluates the quality of sample points in the input dataset and assigns different weight values to samples based on their quality. By applying this method, when using transfer learning on a highly imbalanced new dataset, the accuracy of the transferred model was restored to 92.34% of the original model's performance. Our experiments also revealed that using this loss function structure allowed the model to maintain good stability despite insufficient and imbalanced data. |
| title | FilterLoss: A Transfer Learning Approach for Communication Scene Recognition |
| topic | Econometrics |
| url | https://arxiv.org/abs/2602.07772 |