幻觉提升无监督视觉表征学习的性能
Hallucination Improves the Performance of Unsupervised Visual Representation Learning
AI总结：
针对对比学习正样本对不足、差异不够易过拟合的问题，提出可微的Hallucinator在特征空间生成正样本，降低互信息并平滑，可泛化到多种对比模型，在多个数据集及下游任务中均带来稳定性能提升。
摘要：
基于孪生结构的对比学习模型已在自监督学习中展现出卓越性能。对比学习的这种成功依赖两个条件：充足的正样本对数量，以及正样本对之间足够的差异性。若这些条件未得到满足，这类框架会缺乏语义对比性，且极易出现过拟合。为解决这两个问题，我们提出Hallucinator（幻觉生成器），它能高效生成额外的正样本以用于进一步对比。Hallucinator是可微的，可在特征空间中生成新数据，因此能随预训练任务直接优化，且引入的计算量几乎可以忽略不计。此外，我们降低了生成的样本对之间的互信息，并通过非线性操作对其进行平滑处理。该过程有助于避免对比学习模型在训练过程中出现过度自信的问题，还能获得更具变换不变性的特征嵌入。值得注意的是，我们通过实验证明，所提出的Hallucinator可很好地泛化到多种对比学习模型，包括MoCoV1&V2、SimCLR和SimSiam。在线性分类协议下，该方法在CIFAR10&100、Tiny ImageNet、STL-10和ImageNet数据集上取得了0.3%到3.0%的稳定准确率提升。将预训练编码器迁移到目标检测、分割等下游任务时，也能观察到性能提升。
英文摘要：
Contrastive learning models based on Siamese structure have demonstrated remarkable performance in self-supervised learning. Such a success of contrastive learning relies on two conditions, a sufficient number of positive pairs and adequate variations between them. If the conditions are not met, these frameworks will lack semantic contrast and be fragile on overfitting. To address these two issues, we propose Hallucinator that could efficiently generate additional positive samples for further contrast. The Hallucinator is differentiable and creates new data in the feature space. Thus, it is optimized directly with the pre-training task and introduces nearly negligible computation. Moreover, we reduce the mutual information of hallucinated pairs and smooth them through non-linear operations. This process helps avoid over-confident contrastive learning models during the training and achieves more transformation-invariant feature embeddings. Remarkably, we empirically prove that the proposed Hallucinator generalizes well to various contrastive learning models, including MoCoV1&V2, SimCLR and SimSiam. Under the linear classification protocol, a stable accuracy gain is achieved, ranging from 0.3% to 3.0% on CIFAR10&100, Tiny ImageNet, STL-10 and ImageNet. The improvement is also observed in transferring pre-train encoders to the downstream tasks, including object detection and segmentation.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
