Papers › Self-supervised Implicit Glyph Attention for Text Recognition
Self-supervised Implicit Glyph Attention for Text Recognition
Tongkun Guan, Chaochen Gu, Jingzheng Tu, Xue Yang, Qi Feng, Yudi Zhao, Xiaokang Yang, Wei Shen
The attention mechanism has become the \emph{de facto} module in scene text recognition (STR) methods, due to its capability of extracting character-level representations. These methods can be summarized into implicit attention based and supervised attention based, depended on how the attention is computed, i.e., implicit attention and supervised attention are learned from sequence-level text annotations and or character-level bounding box annotations, respectively. Implicit attention, as it may extract coarse or even incorrect spatial regions as character attention, is prone to suffering from an alignment-drifted issue. Supervised attention can alleviate the above issue, but it is character category-specific, which requires extra laborious character-level bounding box annotations and would be memory-intensive when handling languages with larger character categories. To address the aforementioned issues, we propose a novel attention mechanism for STR, self-supervised implicit glyph attention (SIGA). SIGA delineates the glyph structures of text images by jointly self-supervised text segmentation and implicit attention alignment, which serve as the supervision to improve attention correctness without extra character-level annotations. Experimental results demonstrate that SIGA performs consistently and significantly better than previous attention-based STR methods, in terms of both attention correctness and final recognition performance on publicly available context benchmarks and our contributed contextless benchmarks.
In Syntology View this paper on Syntology: its page in Syntology's graph, with its repositories and citations.
Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Scene Text Recognition | CUTE80 | SIGA_T | Accuracy | 93.1 | #14 of 18 | Archive leaderboard | report |
| Scene Text Recognition | ICDAR 2003 | SIGA_T | Accuracy | 97.0 | #2 of 12 | Archive leaderboard | report |
| Scene Text Recognition | ICDAR2013 | SIGA_T | Accuracy | 97.8 | #12 of 38 | Archive leaderboard | report |
| Scene Text Recognition | ICDAR2015 | SIGA_S | Accuracy | 87.6 | #9 of 27 | Archive leaderboard | report |
| Scene Text Recognition | IIIT5k | SIGA_S | Accuracy | 96.9 | #14 of 17 | Archive leaderboard | report |
| Scene Text Recognition | SVT | SIGA_T | Accuracy | 95.1 | #14 of 37 | Archive leaderboard | report |
| Scene Text Recognition | SVTP | SIGA_T | Accuracy | 90.5 | #14 of 17 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections