Codesota · Models · MTL-TabNet (WS)Nam Tuan Ly / NII3 results · 1 benchmarks
Model card

MTL-TabNet (WS).

Nam Tuan Ly / NIItable-recognition

Weakly-supervised end-to-end multi-task learning for table recognition. Ly et al. (2023), "Nam23WS" variant.

§ 01 · Benchmarks

Every benchmark MTL-TabNet (WS) has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01table-recognition-challenge-mini-testComputer Vision · Table Recognitionteds-all-samples96.0%#7/11source ↗
02table-recognition-challenge-mini-testComputer Vision · Table Recognitionteds-complex-samples94.4%#7/11source ↗
03table-recognition-challenge-mini-testComputer Vision · Table Recognitionteds-simple-samples97.5%#8/11source ↗
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 02 · Strengths by area

Where MTL-TabNet (WS) actually performs.

Computer Vision
1
benchmark
avg rank #7.3
§ 04 · Related models

Other Nam Tuan Ly / NII models scored on Codesota.

MTL-TabNet (GA)
0 results
MTL-TabNet (LA)
0 results
§ 05 · Sources & freshness

Where these numbers come from.

paper
3
results
0 of 3 rows marked verified.