Contrastive instance discrimination outperforms supervised learning in
downstream tasks like image classification and object detection. However, this
approach heavily relies on data augmentation during representation learning,
which may result in inferior results if not properly implemented. Random
cropping followed by resizing is a common form of data augmentation used in
contrastive learning, but it can lead to degraded representation learning if
the two random crops contain distinct semantic content. To address this issue,
this paper introduces LeOCLR (Leveraging Original Images for Contrastive
Learning of Visual Representations), a framework that employs a new instance
discrimination approach and an adapted loss function that ensures the shared
region between positive pairs is semantically correct. The experimental results
show that our approach consistently improves representation learning across
different datasets compared to baseline models. For example, our approach
outperforms MoCo-v2 by 5.1% on ImageNet-1K in linear evaluation and several
other methods on transfer learning tasks.

本论文引入了 LeOCLR（Leveraging Original Images for Contrastive Learning of Visual Representations），一种新的实例辨识方法和适应的损失函数，以保证正样本之间的共享区域在语义上是正确的，实验证明我们的方法在不同数据集上始终比基线模型改进了表征学习。 例如，在线性评估中，我们的方法在 ImageNet-1K 上比 MoCo-v2 提高了 5.1％，在迁移学习任务中也超过了其他几种方法。

LeOCLR: 利用原始图像进行对比学习视觉表征

LeOCLR: Leveraging Original Images for Contrastive Learning of Visual  Representations

Self-supervised learning has recently begun to rival supervised learning on
computer vision tasks. Many of the recent approaches have been based on
contrastive instance discrimination (CID), in which the network is trained to
recognize two augmented versions of the same instance (a query and positive)
while discriminating against a pool of other instances (negatives). The learned
representation is then used on downstream tasks such as image classification.
Using methodology from MoCo v2 (Chen et al., 2020), we divided negatives by
their difficulty for a given query and studied which difficulty ranges were
most important for learning useful representations. We found a minority of
negatives -- the hardest 5% -- were both necessary and sufficient for the
downstream task to reach nearly full accuracy. Conversely, the easiest 95% of
negatives were unnecessary and insufficient. Moreover, the very hardest 0.1% of
negatives were unnecessary and sometimes detrimental. Finally, we studied the
properties of negatives that affect their hardness, and found that hard
negatives were more semantically similar to the query, and that some negatives
were more consistently easy or hard than we would expect by chance. Together,
our results indicate that negatives vary in importance and that CID may benefit
from more intelligent negative treatment.

本文研究采用自监督学习方法对负样本进行分类，发现难度最高的 5% 的负样本对下游任务几乎是必要和充分的，而容易的 95% 负样本则是不必要和不充分的。同时，我们发现难负样本与查询的语义相似度更高，有些负样本的难易程度比预期的要一致。该研究揭示了负样本的重要性差异及其对自监督学习的积极作用。