Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm.

Our paper is available in arxiv


** Our code, dataset and models will be relased soon**


Recently, large-scale Contrastive Language-Image Pre-training (CLIP) (Radfordet al., 2021) has attracted unprecedented attention for its impressive zero-shot recognition ability and excellent transferability to downstream tasks. However, CLIP is quite data-hungry and requires 400M image-text pairs for pre-training, thereby restricting its adoption. This work proposes a novel training paradigm, Data efficient CLIP (DeCLIP), to alleviate this limitation. We demonstrate that by carefully utilizing the widespread supervision among the image-text pairs, our DeCLIP can learn generic visual features more efficiently. Instead of using the single image-text contrastive supervision, we fully exploit data potential through the use of (1) self-supervision within each modality; (2) multi-view supervision across modalities; (3) nearest-neighbor supervision from other similar pairs. Benefiting from these intrinsic supervision, our DeCLIP-ResNet50 can achieve 60.4% zero-shot top1 accuracy on ImageNet, which is 0.8% above the CLIP-ResNet50 while using 7.1× fewer data. Our DeCLIP-ResNet50 outperforms its counterpart in 8 out of 11 visual datasets when transferred to downstream tasks. Moreover, Scaling up the model and computing also works well in our framework.



Our pretrain visual backbone model (w/o text encoder)

DeCLIP_r50 GoogleDriver.
DeCLIP_vitb32 GoogleDriver

Citing DeCLIP

      title={Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm}, 
      author={Yangguang Li and Feng Liang and Lichen Zhao and Yufeng Cui and Wanli Ouyang and Jing Shao and Fengwei Yu and Junjie Yan},


View Github