We present Consistent Assignment of Views over Random Partitions (CARP), a self-supervised clustering method for representation learning of visual features. CARP learns prototypes in an end-to-end online fashion using gradient descent without additional non-differentiable modules to solve the cluster assignment problem. CARP optimizes a new pretext task based on random partitions of prototypes that regularizes the model and enforces consistency between views' assignments. Additionally, our method improves training stability and prevents collapsed solutions in joint-embedding training. Through an extensive evaluation, we demonstrate that CARP's representations are suitable for learning downstream tasks. We evaluate CARP's representations capabilities in 17 datasets across many standard protocols, including linear evaluation, few-shot classification, k-NN, k-means, image retrieval, and copy detection. We compare CARP performance to 11 existing self-supervised methods. We extensively ablate our method and demonstrate that our proposed random partition pretext task improves the quality of the learned representations by devising multiple random classification tasks. In transfer learning tasks, CARP achieves the best performance on average against many SSL methods trained for a longer time.

翻译：我们提出了基于随机划分视图一致分配（CARP）方法，这是一种用于视觉特征表示学习的自监督聚类方法。CARP通过梯度下降以端到端在线方式学习原型，无需额外的不可微模块来解决聚类分配问题。CARP优化了一个基于原型随机划分的新前置任务，该任务可正则化模型并强制视图间分配的一致性。此外，我们的方法提高了训练稳定性，并防止了联合嵌入训练中的崩溃解。通过广泛评估，我们证明CARP的表示适用于学习下游任务。我们在17个数据集上评估了CARP的表示能力，遵循多种标准协议，包括线性评估、少样本分类、k近邻、k均值、图像检索和拷贝检测。我们将CARP的性能与11种现有自监督方法进行了比较。我们对方法进行了全面消融实验，证明所提出的随机划分前置任务通过设计多个随机分类任务，提升了学习表示的质量。在迁移学习任务中，CARP在平均性能上优于许多经过更长时间训练的SSL方法。