We introduce an approach to building a custom model from ready-made self-supervised models via their associating instead of training and fine-tuning. We demonstrate it with an example of a humanoid robot looking at the mirror and learning to detect the 3D pose of its own body from the image it perceives. To build our model, we first obtain features from the visual input and the postures of the robot's body via models prepared before the robot's operation. Then, we map their corresponding latent spaces by a sample-efficient robot's self-exploration at the mirror. In this way, the robot builds the solicited 3D pose detector, which quality is immediately perfect on the acquired samples instead of obtaining the quality gradually. The mapping, which employs associating the pairs of feature vectors, is then implemented in the same way as the key-value mechanism of the famous transformer models. Finally, deploying our model for imitation to a simulated robot allows us to study, tune up, and systematically evaluate its hyperparameters without the involvement of the human counterpart, advancing our previous research.

翻译：我们提出一种方法，通过关联现成的自监督模型而非训练或微调来构建定制模型。以类人机器人照镜子并从感知图像中学习检测自身三维姿态为例进行演示。为构建模型，我们首先通过机器人运行前预训练的模型提取视觉输入特征与机器人身体姿态特征，随后利用机器人在镜子前进行样本高效的自我探索，对齐其对应的潜在空间。通过这种方式，机器人构建了所需的三维姿态检测器——其质量在获取样本时即刻达到完美，而非逐步提升。该映射过程采用特征向量对关联方法，与著名Transformer模型的键值机制原理相同。最后，将模型部署至仿真机器人进行模仿学习，使我们能在无需人类参与者的情况下研究、调优并系统评估其超参数，从而推进先前研究。