Superpixel graphs (statistics in Table S1) gain from all augmentations except attribute masking as shown in Figure S1. D Difficulty of Contrastive T asks v.s. Pairing "Identical" stands for a no-augmentation baseline for contrastive The baseline training-from-scratch accuracy is 79.71%. Performance on contrastive learning with different implemented subgraph. For subgraph, we propose the following variants with difficulty levels.

This general framework encapsulates numerous variations of learning in linear control that have been studied extensively in the literature. When the system parameters are known ahead of time and the costs are fixed and known (convex) quadratics, this amounts to the classical "planning"

Our simple approach results insuperior performance compared toprevious methods. Despite this improvement, we further identify a common-action bias issue that the cross-modal baseline over-focus on common sub-actions due to a lack of ability todiscriminate text-related visual parts.