LXMERT: Learning Cross-Modality Encoder Representations from Transformers

Benchmark Model Rank Results
visual-question-answering-on-gqa-test2019LXR955, Ensemble#3Accuracy: 62.71Binary: 79.79Open: 47.64Consistency: 93.1…
visual-question-answering-on-gqa-test2019LXR955, Single Model#4Accuracy: 60.33Binary: 77.16Open: 45.47Consistency: 89.59…
visual-question-answering-on-gqa-test-stdLXMERT#4Accuracy: 60.3
visual-question-answering-on-a-okvqaLXMERT#6MC Accuracy: 41.6DA VQA Score: 25.9
visual-question-answering-on-gqa-test-devLXMERT (Pre-train + scratch)#7Accuracy: 60.0
visual-reasoning-on-nlvr2-devLXMERT (Pre-train + scratch)#14Accuracy: 74.9
visual-reasoning-on-nlvr2-testLXMERT#15Accuracy: 76.2
visual-question-answering-on-vqa-v2-test-stdLXMERT#22overall: 72.5
visual-question-answering-on-vqa-v2-test-devLXMERT (Pre-train + scratch)#32Accuracy: 69.9