Multimodal Multiclass Classification on FOOD-101 (test)
94.6AccuracyME
Evaluation Results
| Method | Links | |
|---|---|---|
| MEFusion AGG=false, Fusion ALI=true, Backbone Image=DenseNet, Backbone Text=BERT2023.05 | 94.6 | |
| MLAModality=Multi2023.11 | 93.33 | |
| MMBT-LargeModel Scale=Large2019.09 | 93.2 | |
| CMA-CLIPFusion AGG=true, Fusion ALI=true, Backbone Image=ViT, Backbone Text=Transformer2023.05 | 93.1 | |
| ViLBertFine-tuning Source=Standard pre-trained2019.09 | 92.9 | |
| QMFModality=Multi2023.11 | 92.87 | |
| HUSEFusion AGG=true, Fusion ALI=true, Backbone Image=Graph-RISE, Backbone Text=BERT2023.05 | 92.3 | |
| ViLBert-RefcocoFine-tuning Source=Refcoco2019.09 | 92.2 | |
| ViLBert-Flickr30kFine-tuning Source=Flickr30k2019.09 | 92.2 | |
| MMBT2019.09 | 92.1 | |
| MMBTModel Scale=Base2019.09 | 92.1 | |
| ViLBert-VQAFine-tuning Source=VQA2019.09 | 92.1 | |
| ViLBert-VCRFine-tuning Source=VCR2019.09 | 92.1 | |
| ViLTFusion AGG=true, Fusion ALI=true, Backbone Image=ViT, Backbone Text=BERT2023.05 | 92 | |
| Late FusionDescription=Averages scores of Bert and Img classifiers2019.09 | 91.1 | |
| Bilinear-gated (BG)2019.09 | 90.8 | |
| Late FusionModality=Multi2023.11 | 90.21 | |
| FiLMBertDescription=FiLM + BERT, Backbone=ResNet-152 features2019.09 | 90.2 | |
| ConcatBertDescription=Concatenation of Bert and Img baselines2019.09 | 90 | |
| BiGatedModality=Multi2023.11 | 88.87 | |
| OGM-GEModality=Multi2023.11 | 87.54 | |
| FiLMModality=Multi2023.11 | 87.21 | |
| BertModality=Text-only, Backbone=BERT base-uncased2019.09 | 87.2 | |
| MLAModality=Text2023.11 | 86.47 | |
| ConcatModality=Multi2023.11 | 86.32 | |
| SumModality=Multi2023.11 | 86.19 | |
| ConcatModality=Text2023.11 | 86.02 | |
| FiLMModality=Text2023.11 | 85.84 | |
| BiGatedModality=Text2023.11 | 85.79 | |
| SumModality=Text2023.11 | 85.63 | |
| Late FusionModality=Text2023.11 | 85.19 | |
| OGM-GEModality=Text2023.11 | 85.17 | |
| Word2vec+VGGNet (W+V)2019.09 | 85.1 | |
| QMFModality=Text2023.11 | 84.13 | |
| ConcatBowDescription=Concatenation of Bow and Img baselines2019.09 | 79 | |
| BowModality=Text-only2019.09 | 72.4 | |
| MLAModality=Image2023.11 | 69.6 | |
| ImgModality=Image-only, Backbone=ResNet-1522019.09 | 63.2 | |
| Late FusionModality=Image2023.11 | 58.46 | |
| QMFModality=Image2023.11 | 45.74 | |
| OGM-GEModality=Image2023.11 | 22.35 | |
| BiGatedModality=Image2023.11 | 14.2 | |
| FiLMModality=Image2023.11 | 4.68 | |
| SumModality=Image2023.11 | 4.57 | |
| ConcatModality=Image2023.11 | 3.51 |