Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

FastTab: A Fast Table Recognizer with a Tiny Recursive Module and 1D Transformers

About

Table structure recognition (TSR) requires both table-level coherence (row/column counts, headers, spanning cells) and precise separator localization. We introduce FastTab, a grid-centric TSR model that avoids autoregressive HTML decoding by combining (i) a lightweight Tiny Recursive Module (TRM) for global reasoning and (ii) axial 1D Transformer encoders that capture long-range dependencies along rows and columns. The model predicts row/column counts, header rows, and separators to construct a grid, then infers rowspan/colspan using ROI-aligned cell features. Across four benchmarks (PubTabNet, FinTabNet, PubTables-1M, and SciTSR), FastTab achieves competitive structure recovery performance while operating at low-latency inference. We further study robustness under pixel-level anonymisation and show an extension to curved separators for camera-captured documents. The source code will be made publicly available at https://github.com/hamdilaziz/FastTab .

Laziz Hamdi, Amine Tamasna, Pascal Boisson, Thierry Paquet• 2026

Related benchmarks

TaskDatasetResultRank
Table RecognitionPubTabNet (test)
TEDS (Simple)96.8
70
Table Structure RecognitionSciTSR (test)
F1 Score99.5
15
Table Structure RecognitionPubTables-1M
GriTS Top Score98.27
15
Table RecognitionFinTabNet (test)
S-TEDS98.2
13
Showing 4 of 4 rows

Other info

Follow for update