OneChart: Purify the Chart Structural Extraction via One Auxiliary Token
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916222141988864 |
|---|---|
| author | Chen, Jinyue Kong, Lingyu Wei, Haoran Liu, Chenglong Ge, Zheng Zhao, Liang Sun, Jianjian Han, Chunrui Zhang, Xiangyu |
| author_facet | Chen, Jinyue Kong, Lingyu Wei, Haoran Liu, Chenglong Ge, Zheng Zhao, Liang Sun, Jianjian Han, Chunrui Zhang, Xiangyu |
| contents | Chart parsing poses a significant challenge due to the diversity of styles, values, texts, and so forth. Even advanced large vision-language models (LVLMs) with billions of parameters struggle to handle such tasks satisfactorily. To address this, we propose OneChart: a reliable agent specifically devised for the structural extraction of chart information. Similar to popular LVLMs, OneChart incorporates an autoregressive main body. Uniquely, to enhance the reliability of the numerical parts of the output, we introduce an auxiliary token placed at the beginning of the total tokens along with an additional decoder. The numerically optimized (auxiliary) token allows subsequent tokens for chart parsing to capture enhanced numerical features through causal attention. Furthermore, with the aid of the auxiliary token, we have devised a self-evaluation mechanism that enables the model to gauge the reliability of its chart parsing results by providing confidence scores for the generated content. Compared to current state-of-the-art (SOTA) chart parsing models, e.g., DePlot, ChartVLM, ChartAst, OneChart significantly outperforms in Average Precision (AP) for chart structural extraction across multiple public benchmarks, despite enjoying only 0.2 billion parameters. Moreover, as a chart parsing agent, it also brings 10%+ accuracy gains for the popular LVLM (LLaVA-1.6) in the downstream ChartQA benchmark. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_09987 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | OneChart: Purify the Chart Structural Extraction via One Auxiliary Token Chen, Jinyue Kong, Lingyu Wei, Haoran Liu, Chenglong Ge, Zheng Zhao, Liang Sun, Jianjian Han, Chunrui Zhang, Xiangyu Computer Vision and Pattern Recognition Chart parsing poses a significant challenge due to the diversity of styles, values, texts, and so forth. Even advanced large vision-language models (LVLMs) with billions of parameters struggle to handle such tasks satisfactorily. To address this, we propose OneChart: a reliable agent specifically devised for the structural extraction of chart information. Similar to popular LVLMs, OneChart incorporates an autoregressive main body. Uniquely, to enhance the reliability of the numerical parts of the output, we introduce an auxiliary token placed at the beginning of the total tokens along with an additional decoder. The numerically optimized (auxiliary) token allows subsequent tokens for chart parsing to capture enhanced numerical features through causal attention. Furthermore, with the aid of the auxiliary token, we have devised a self-evaluation mechanism that enables the model to gauge the reliability of its chart parsing results by providing confidence scores for the generated content. Compared to current state-of-the-art (SOTA) chart parsing models, e.g., DePlot, ChartVLM, ChartAst, OneChart significantly outperforms in Average Precision (AP) for chart structural extraction across multiple public benchmarks, despite enjoying only 0.2 billion parameters. Moreover, as a chart parsing agent, it also brings 10%+ accuracy gains for the popular LVLM (LLaVA-1.6) in the downstream ChartQA benchmark. |
| title | OneChart: Purify the Chart Structural Extraction via One Auxiliary Token |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.09987 |