Retrieval on MS-COCO Flickr30k
14.6Mean RecallFinal Self-Filtered 30% Data Mix
Evaluation Results
| Method | Links | |
|---|---|---|
| Final Self-Filtered 30% Data MixBackbone=ViT-B/32, Data=Final data mix from last round of Self-Filtering, Evaluation Protocol=Zero-shot2026.06 | 14.6 | |
| Self-Filtering 30%Backbone=ViT-B/32, Data=30% subset selected via Self-Filtering, Evaluation Protocol=Zero-shot2026.06 | 14.5 | |
| CLIP with OAI CLIP Filtered data + AllBackbone=ViT-B/32, Data=OAI Filtered + All data mix, Evaluation Protocol=Zero-shot2026.06 | 14.4 | |
| Self-Filtering 40%Backbone=ViT-B/32, Data=40% subset selected via Self-Filtering, Evaluation Protocol=Zero-shot2026.06 | 14.2 | |
| CLIP with All dataBackbone=ViT-B/32, Data=11.49M samples (Datacomp small), Evaluation Protocol=Zero-shot2026.06 | 14.1 | |
| CLIP with OAI CLIP Filtered dataBackbone=ViT-B/32, Data=Data selected by OpenAI’s CLIP ViT-L/14, Evaluation Protocol=Zero-shot2026.06 | 10.2 |