PeCLR: Self-Supervised 3D Hand Pose Estimation from monocular RGB via Equivariant Contrastive Learning
This addresses the problem of accurate 3D hand pose estimation for applications like human-computer interaction, though it is incremental as it adapts contrastive learning to a specific task.
The paper tackles 3D hand pose estimation from monocular RGB images by proposing a self-supervised method using equivariant contrastive learning, achieving up to 14.5% improvement in PA-EPE on FreiHAND and state-of-the-art performance without specialized architectures.
Encouraged by the success of contrastive learning on image classification tasks, we propose a new self-supervised method for the structured regression task of 3D hand pose estimation. Contrastive learning makes use of unlabeled data for the purpose of representation learning via a loss formulation that encourages the learned feature representations to be invariant under any image transformation. For 3D hand pose estimation, it too is desirable to have invariance to appearance transformation such as color jitter. However, the task requires equivariance under affine transformations, such as rotation and translation. To address this issue, we propose an equivariant contrastive objective and demonstrate its effectiveness in the context of 3D hand pose estimation. We experimentally investigate the impact of invariant and equivariant contrastive objectives and show that learning equivariant features leads to better representations for the task of 3D hand pose estimation. Furthermore, we show that standard ResNets with sufficient depth, trained on additional unlabeled data, attain improvements of up to 14.5% in PA-EPE on FreiHAND and thus achieves state-of-the-art performance without any task specific, specialized architectures. Code and models are available at https://ait.ethz.ch/projects/2021/PeCLR/