# Enhancing Vietnamese VQA through Curriculum Learning on Raw and Augmented Text Representations

arXiv: https://arxiv.org/abs/2503.03285 · HTML: https://mlsanity.com/paper/2503.03285/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 29 references that are in the map.
- First posted on arXiv 5 Mar 2025.

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [mT5: A massively multilingual pre-trained text-to-text transformer](https://mlsanity.com/paper/2010.11934/) (2020)
- [LXMERT: Learning Cross-Modality Encoder Representations from Transformers](https://mlsanity.com/paper/1908.07490/) (2019)
- [VisualBERT: A Simple and Performant Baseline for Vision and Language](https://mlsanity.com/paper/1908.03557/) (2019)
- [Mixed Precision Training](https://mlsanity.com/paper/1710.03740/) (2017)
- [BEiT v2: Masked Image Modeling with Vector-Quantized Visual Tokenizers](https://mlsanity.com/paper/2208.06366/) (2022)
- [PhoBERT: Pre-trained language models for Vietnamese](https://mlsanity.com/paper/2003.00744/) (2020)
- [Dynamic Curriculum Learning for Imbalanced Data Classification](https://mlsanity.com/paper/1901.06783/) (2019)
- [Semantic Equivalent Adversarial Data Augmentation for Visual Question Answering](https://mlsanity.com/paper/2007.09592/) (2020)
- [OpenViVQA: Task, Dataset, and Multimodal Fusion Models for Visual Question Answering in Vietnamese](https://mlsanity.com/paper/2305.04183/) (2023)
- [TAG: Boosting Text-VQA via Text-aware Visual Question-answer Generation](https://mlsanity.com/paper/2208.01813/) (2022)
- [Towards Robust Natural-Looking Mammography Lesion Synthesis on Ipsilateral Dual-Views Breast Cancer Analysis](https://mlsanity.com/paper/2309.03506/) (2023)
- [Delving into Ipsilateral Mammogram Assessment under Multi-View Network](https://mlsanity.com/paper/2309.02197/) (2023)
- [Improving Data Augmentation for Robust Visual Question Answering with Effective Curriculum Learning](https://mlsanity.com/paper/2401.15646/) (2024)

## Built on by (most cited first, 4 of 4)

- [A Lightweight Moment Retrieval System with Global Re-Ranking and Robust Adaptive Bidirectional Temporal Search](https://mlsanity.com/paper/2504.09298/) (2025)
- [Describe Anything Model for Visual Question Answering on Text-rich Images](https://mlsanity.com/paper/2507.12441/) (2025)
- [Cycle Training with Semi-Supervised Domain Adaptation: Bridging Accuracy and Efficiency for Real-Time Mobile Scene Detection](https://mlsanity.com/paper/2504.09297/) (2025)
- [Towards Efficient and Robust Moment Retrieval System: A Unified Framework for Multi-Granularity Models and Temporal Reranking](https://mlsanity.com/paper/2504.08384/) (2025)

## Abstract (arXiv)

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.