Siamese networks are one of the most trending methods to achieve self-supervised visual representation learning (SSL). Since hand labeling is costly, SSL can play a crucial part by allowing deep learning to train on large unlabeled datasets. Meanwhile, Neural Architecture Search (NAS) is becoming increasingly important as a technique to discover novel deep learning architectures. However, early NAS methods based on reinforcement learning or evolutionary algorithms suffered from ludicrous computational and memory costs. In contrast, differentiable NAS, a gradient-based approach, has the advantage of being much more efficient and has thus retained most of the attention in the past few years. In this article, we present NASiam, a novel approach that uses for the first time differentiable NAS to improve the multilayer perceptron projector and predictor (encoder/predictor pair) architectures inside siamese-networks-based contrastive learning frameworks (e.g., SimCLR, SimSiam, and MoCo) while preserving the simplicity of previous baselines. We crafted a search space designed explicitly for multilayer perceptrons, inside which we explored several alternatives to the standard ReLU activation function. We show that these new architectures allow ResNet backbone convolutional models to learn strong representations efficiently. NASiam reaches competitive performance in both small-scale (i.e., CIFAR-10/CIFAR-100) and large-scale (i.e., ImageNet) image classification datasets while costing only a few GPU hours. We discuss the composition of the NAS-discovered architectures and emit hypotheses on why they manage to prevent collapsing behavior. Our code is available at https://github.com/aheuillet/NASiam.

翻译：孪生网络是当下实现自监督视觉表示学习（SSL）最流行的方法之一。由于人工标注成本高昂，SSL通过允许深度学习在大规模无标注数据集上训练而发挥关键作用。与此同时，神经架构搜索（NAS）作为发现新型深度学习架构的技术日益重要。然而，早期基于强化学习或进化算法的NAS方法存在计算与存储成本过高的缺陷。相比之下，可微NAS作为一种梯度方法具有高效优势，近年持续获得广泛关注。本文提出NASiam这一创新方法，首次利用可微NAS改进基于孪生网络的对比学习框架（如SimCLR、SimSiam和MoCo）中的多层感知机投影器与预测器（编码器/预测器对）架构，同时保持基线方法的简洁性。我们专门设计了面向多层感知机的搜索空间，在其中探索了多种替代标准ReLU激活函数的方案。实验表明，这些新架构能使ResNet骨干卷积模型高效学习强表征。NASiam在小型（CIFAR-10/CIFAR-100）和大型（ImageNet）图像分类数据集上均达到具有竞争力的性能，且仅需数GPU小时。我们讨论了NAS发现架构的构成，并提出了防止崩溃行为的假设。代码已开源至https://github.com/aheuillet/NASiam。