EmbraceNet (image+text)

Reported on 6 benchmarks across 3 tasks · 1 paper · 6 SOTA

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

Miscellaneous4 results

Multi-modal ClassificationonGLAMI-1M
Top 1 Accuracy %· uses extra data· 2022-11-17
69.7
SOTA
GLAMI-1M: A Multilingual Image-Text Fashion Dataset arXiv:2211.14451
Multi-modal ClassificationonGLAMI-1M
Top 5 Accuracy %· uses extra data· 2022-11-17
94
SOTA
GLAMI-1M: A Multilingual Image-Text Fashion Dataset arXiv:2211.14451
Image-text ClassificationonGLAMI-1M
Top 1 Accuracy %· uses extra data· 2022-11-17
69.7
SOTA
GLAMI-1M: A Multilingual Image-Text Fashion Dataset arXiv:2211.14451
Image-text ClassificationonGLAMI-1M
Top 5 Accuracy %· uses extra data· 2022-11-17
94
SOTA
GLAMI-1M: A Multilingual Image-Text Fashion Dataset arXiv:2211.14451

Methodology2 results

ClassificationonGLAMI-1M
Top 1 Accuracy %· uses extra data· 2022-11-17
69.7
SOTA
GLAMI-1M: A Multilingual Image-Text Fashion Dataset arXiv:2211.14451
ClassificationonGLAMI-1M
Top 5 Accuracy %· uses extra data· 2022-11-17
94
SOTA
GLAMI-1M: A Multilingual Image-Text Fashion Dataset arXiv:2211.14451