Enhancing Vietnamese VQA through Curriculum Learning on Raw and Augmented Text Representations
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917946870202368 |
|---|---|
| author | Nguyen, Khoi Anh Vu, Linh Yen Duong, Thang Dinh Duong, Thuan Nguyen Nguyen, Huy Thanh Dinh, Vinh Quang |
| author_facet | Nguyen, Khoi Anh Vu, Linh Yen Duong, Thang Dinh Duong, Thuan Nguyen Nguyen, Huy Thanh Dinh, Vinh Quang |
| contents | Visual Question Answering (VQA) is a multimodal task requiring reasoning across textual and visual inputs, which becomes particularly challenging in low-resource languages like Vietnamese due to linguistic variability and the lack of high-quality datasets. Traditional methods often rely heavily on extensive annotated datasets, computationally expensive pipelines, and large pre-trained models, specifically in the domain of Vietnamese VQA, limiting their applicability in such scenarios. To address these limitations, we propose a training framework that combines a paraphrase-based feature augmentation module with a dynamic curriculum learning strategy. Explicitly, augmented samples are considered "easy" while raw samples are regarded as "hard". The framework then utilizes a mechanism that dynamically adjusts the ratio of easy to hard samples during training, progressively modifying the same dataset to increase its difficulty level. By enabling gradual adaptation to task complexity, this approach helps the Vietnamese VQA model generalize well, thus improving overall performance. Experimental results show consistent improvements on the OpenViVQA dataset and mixed outcomes on the ViVQA dataset, highlighting both the potential and challenges of our approach in advancing VQA for Vietnamese language. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_03285 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Enhancing Vietnamese VQA through Curriculum Learning on Raw and Augmented Text Representations Nguyen, Khoi Anh Vu, Linh Yen Duong, Thang Dinh Duong, Thuan Nguyen Nguyen, Huy Thanh Dinh, Vinh Quang Computer Vision and Pattern Recognition Machine Learning Visual Question Answering (VQA) is a multimodal task requiring reasoning across textual and visual inputs, which becomes particularly challenging in low-resource languages like Vietnamese due to linguistic variability and the lack of high-quality datasets. Traditional methods often rely heavily on extensive annotated datasets, computationally expensive pipelines, and large pre-trained models, specifically in the domain of Vietnamese VQA, limiting their applicability in such scenarios. To address these limitations, we propose a training framework that combines a paraphrase-based feature augmentation module with a dynamic curriculum learning strategy. Explicitly, augmented samples are considered "easy" while raw samples are regarded as "hard". The framework then utilizes a mechanism that dynamically adjusts the ratio of easy to hard samples during training, progressively modifying the same dataset to increase its difficulty level. By enabling gradual adaptation to task complexity, this approach helps the Vietnamese VQA model generalize well, thus improving overall performance. Experimental results show consistent improvements on the OpenViVQA dataset and mixed outcomes on the ViVQA dataset, highlighting both the potential and challenges of our approach in advancing VQA for Vietnamese language. |
| title | Enhancing Vietnamese VQA through Curriculum Learning on Raw and Augmented Text Representations |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2503.03285 |