While self-supervised representation learning (SSL) has received widespread attention from the community, recent research argue that its performance will suffer a cliff fall when the model size decreases. The current method mainly relies on contrastive learning to train the network and in this work, we propose a simple yet effective Distilled Contrastive Learning (DisCo) to ease the issue by a large margin. Specifically, we find the final embedding obtained by the mainstream SSL methods contains the most fruitful information, and propose to distill the final embedding to maximally transmit a teacher's knowledge to a lightweight model by constraining the last embedding of the student to be consistent with that of the teacher. In addition, in the experiment, we find that there exists a phenomenon termed Distilling BottleNeck and present to enlarge the embedding dimension to alleviate this problem. Our method does not introduce any extra parameter to lightweight models during deployment. Experimental results demonstrate that our method achieves the state-of-the-art on all lightweight models. Particularly, when ResNet-101/ResNet-50 is used as teacher to teach EfficientNet-B0, the linear result of EfficientNet-B0 on ImageNet is very close to ResNet-101/ResNet-50, but the number of parameters of EfficientNet-B0 is only 9.4\%/16.3\% of ResNet-101/ResNet-50. Code is available at https://github. com/Yuting-Gao/DisCo-pytorch.
翻译:虽然自我监督的代表学习(SSL)得到了社区的广泛关注,但最近的研究表明,当模型规模缩小时,其表现将受到悬崖式下降的影响。目前的方法主要依靠对比性学习来培训网络和这项工作,我们提出一个简单而有效的蒸馏对比学习(Disco)来大大缓解这一问题。具体地说,我们发现主流SSL方法的最终嵌入包含最有成果的信息,并提议通过限制学生最后一次嵌入与教师的嵌入,将教师的知识最大限度地传递到轻量模型中。此外,在实验中,我们发现存在一种叫蒸馏BottleNeck并正在扩大嵌入层面以缓解这一问题的现象。我们的方法不会在部署期间对轻量模型引入任何额外的参数。实验结果显示,我们的方法在所有轻量模型上都达到了最新水平。特别是当ResNet-101/ResNet-50作为教师最接近的嵌入点时, ASNet-50-Net-Netxal AS-ROQQQONB的运行结果是SS-ROQQ-RONB AS-SANS-NLOQ ISNLOQQQQ ISNEMONLONEM ISNET ISQQQQQQQQQQQQQLISNEMOQQQQQQQQQQQQQQQQLONEMONLISNLONLONLOQQQLOQLOQLOQLOQLOQLOQLISNB ISNB SSLINSG/QLLLLLINSLINS/QLISDLO/QLO/QLO/QLISDLISDLISDLISDLOQLO/QLISDLINSLO/QLO/QLODLODLODLLLLLLLODLOBDLOBDLOBDLOBDLOBDLDLDLLIFF的运行的运行的线性结果。