List your company

Image-Text Retrieval on LVIS

22Recall@1CLIP-ViT-L/14
6.909610.827314.74518.6627Aug 31, 2022

Evaluation results

MethodLinks
CLIP-ViT-L/14Single Feature=No, Input=CC@102022.0822
InternVL-C (MLLM)Single Feature=Yes, Input=Full Image2022.0816.81
DetailCLIP-ViT-L/14Single Feature=Yes, Input=CC@102022.0815.29
CLIP-ViT-L/14Single Feature=Yes, Input=Full Image2022.0815.12
GLIP (detector/grounding-based)Single Feature=Yes, Input=Full Image2022.0813.75
BLIP2 (CLIP-like)Single Feature=Yes, Input=Full Image2022.0813.36
MDETR (detector/grounding-based)Single Feature=Yes, Input=Full Image2022.0812.24
RegionCLIP (detector-based)Single Feature=Yes, Input=Full Image2022.0810.13
SLIP (CLIP-like)Single Feature=Yes, Input=Full Image2022.089.65
CLIP-ViT-B/16Single Feature=No, Input=CC@102022.089.4
DetailCLIP-ViT-B/16Single Feature=Yes, Input=CC@102022.087.66
CLIP-ViT-B/16Single Feature=Yes, Input=Full Image2022.087.49