LXMERT (low-magnitude pruning)

Reported on 4 benchmarks across 2 tasks · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing4 results

Visual Question Answering (VQA)onVQA v2 test-std
Accuracy· 2023-10-23
70.87
SOTA
LXMERT Model Compression for Visual Question Answering arXiv:2310.15325
Visual Question AnsweringonVQA v2 test-std
Accuracy· 2023-10-23
70.87
SOTA
LXMERT Model Compression for Visual Question Answering arXiv:2310.15325
Visual Question Answering (VQA)onVQA v2 test-dev
Accuracy· 2023-10-23
70.72
best: 84.3 (PaLI)
LXMERT Model Compression for Visual Question Answering arXiv:2310.15325
Visual Question AnsweringonVQA v2 test-dev
Accuracy· 2023-10-23
70.72
best: 82.3 (BLIP-2 ViT-G OPT 6.7B (fine-tuned))
LXMERT Model Compression for Visual Question Answering arXiv:2310.15325