Multi-task Learning with 3D-Aware Regularization
This work addresses performance issues in multi-task learning for computer vision, offering an incremental improvement through a plug-in regularizer.
The paper tackles the problem of noisy cross-task correlations in multi-task learning for dense computer vision tasks by introducing a structured 3D-aware regularizer that projects features into a shared 3D space, improving performance on benchmarks like NYUv2 and PASCAL-Context.
Deep neural networks have become a standard building block for designing models that can perform multiple dense computer vision tasks such as depth estimation and semantic segmentation thanks to their ability to capture complex correlations in high dimensional feature space across tasks. However, the cross-task correlations that are learned in the unstructured feature space can be extremely noisy and susceptible to overfitting, consequently hurting performance. We propose to address this problem by introducing a structured 3D-aware regularizer which interfaces multiple tasks through the projection of features extracted from an image encoder to a shared 3D feature space and decodes them into their task output space through differentiable rendering. We show that the proposed method is architecture agnostic and can be plugged into various prior multi-task backbones to improve their performance; as we evidence using standard benchmarks NYUv2 and PASCAL-Context.