TCL, a CPU-trained contrastive encoder for tabular data, reports higher F1 than FT-Transformer and ResNet on most OOD classification datasets, but the result is not statistically supported.
Towards open set deep net- works,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Representation Learning on Out of Distribution in Tabular Data
TCL, a CPU-trained contrastive encoder for tabular data, reports higher F1 than FT-Transformer and ResNet on most OOD classification datasets, but the result is not statistically supported.