Contrastive representation learning has proven to be an effective self-supervised learning method for images and videos. Most successful approaches are based on Noise Contrastive Estimation (NCE) and use different views of an instance as positives that should be contrasted with other instances, called negatives, that are considered as noise. However, several instances in a dataset are drawn from the same distribution and share underlying semantic information. A good data representation should contain relations between the instances, or semantic similarity and dissimilarity, that contrastive learning harms by considering all negatives as noise. To circumvent this issue, we propose a novel formulation of contrastive learning using semantic similarity between instances called Similarity Contrastive Estimation (SCE). Our training objective is a soft contrastive one that brings the positives closer and estimates a continuous distribution to push or pull negative instances based on their learned similarities. We validate empirically our approach on both image and video representation learning. We show that SCE performs competitively with the state of the art on the ImageNet linear evaluation protocol for fewer pretraining epochs and that it generalizes to several downstream image tasks. We also show that SCE reaches state-of-the-art results for pretraining video representation and that the learned representation can generalize to video downstream tasks.

我们提出了一项新的自我监督的预测变压器预测，以进行密集的预测任务。它基于将像素级表示与全局图像表示形式进行比较的对比损失。该策略可产生更好的本地功能，适用于密集的预测任务，而不是基于全球图像表示的对比预训练。此外，我们的方法不会遭受批次大小的减小，因为对比度损失所需的负面示例数量是局部特征数量的顺序。我们证明了训练策略对两个密集预测任务的有效性：语义分割和单眼深度估计。

对比表现学习已被证明是一种有效的自我监督学习方法。大多数成功的方法都是基于噪声对比估计（NCE）范式，并将实例视图的视图视为阳性和其他情况，作为阳性应与其对比的噪声。但是，数据集中的所有实例都是从相同的分布和共享底层语义信息中汲取，这些语义信息不应被视为噪声。我们认为，良好的数据表示包含实例之间的关系或语义相似性。对比学习隐含地学习关系，但认为负面的噪音是对学习关系质量有害的噪音，因此是象征性的质量。为了规避这个问题，我们提出了一种使用称为相似性对比估计（SCE）之间的情况之间的语义相似性的对比学习的新颖性。我们的培训目标可以被视为柔和的对比学习。我们提出了持续分配以基于其语义相似性推动或拉动实例的持续分配。目标相似性分布从弱增强的情况计算并锐化以消除无关的关系。每个弱增强实例都与一个强大的增强实例配对，该实例对比其积极的同时保持目标相似性分布。实验结果表明，我们所提出的SCE在各种数据集中优于其基线MoCov2和RESSL，并对ImageNet线性评估协议上的最先进的算法具有竞争力。