Research map / Image generation / Text-to-image diffusion
SGBANet: Semantic GAN and Balanced Attention Network for Arbitrarily Oriented Scene Text Recognition
Dajian Zhong, Shujing Lyu, Palaiahnakote Shivakumara, Bing Yin, Jiajia Wu, Umapada Pal, Yue Lu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add Semantic GAN (ablation) | Baseline · IIIT5K | accuracy: 90.1 -> 92.1 | Improved |
| add Semantic GAN (ablation) | Baseline · SVT | accuracy: 84.5 -> 86.6 | Improved |
| add Semantic GAN (ablation) | Baseline · IC13 | accuracy: 91.8 -> 91.1 | Hurt |
| add Semantic GAN (ablation) | Baseline · IC15 | accuracy: 70.5 -> 72.5 | Improved |
| add Semantic GAN (ablation) | Baseline · CUTE80 | accuracy: 80.0 -> 80.5 | Improved |
| add Balanced Attention (ablation) | Baseline+SGAN · IC15 | accuracy: 72.5 -> 78.4 | Improved |
| add Balanced Attention (ablation) | Baseline+SGAN · SVTP | accuracy: 77.1 -> 83.1 | Improved |
| add Balanced Attention (ablation) | Baseline+SGAN · CUTE80 | accuracy: 80.5 -> 88.2 | Improved |
| add Balanced Attention (ablation) | Baseline+SGAN · IIIT5K | accuracy: 92.1 -> 95.4 | Improved |
| learned balancing instead of plain addition of glimpse vectors (ablation) | Balanced Attention · SVT | accuracy: 89.4 -> 89.1 | Mixed |
| learned balancing instead of plain addition of glimpse vectors (ablation) | Balanced Attention · IC15 | accuracy: 77.3 -> 78.4 | Improved |
| learned balancing instead of concatenate-and-FC (ablation) | Balanced Attention · CUTE80 | accuracy: 88.5 -> 88.2 | Mixed |
Closest papers by meaning
- Towards Accurate Scene Text Recognition With Semantic Reasoning Networks (CVPR 2020 · similarity 0.86)
- Verisimilar Image Synthesis for Accurate Detection and Recognition of Texts in Scenes (ECCV 2018 · similarity 0.85)
- Focusing Attention: Towards Accurate Text Recognition in Natural Images (ICCV 2017 · similarity 0.85)
- Image as a Language: Revisiting Scene Text Recognition via Balanced, Unified and Synchronized Vision-Language Reasoning Network (AAAI 2024 · similarity 0.85)
- IPAD: Iterative, Parallel, and Diffusion-Based Network for Scene Text Recognition (IJCV 2025 · similarity 0.85)
- Visual Semantics Allow for Textual Reasoning Better in Scene Text Recognition (AAAI 2022 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
