Learning Bidirectional Translation between Descriptions and Actions with Small Paired Data
This work addresses the challenge of enabling robots to collaborate with humans by generating descriptions and actions, but it is incremental as it builds on existing translation methods with a focus on data efficiency.
This study tackled the problem of bidirectional translation between descriptions and actions using small paired datasets, proposing a two-stage training method that leverages non-paired data for pre-training and achieves good performance with limited paired data, as shown in experimental evaluations with motion-captured actions and descriptions.
This study achieved bidirectional translation between descriptions and actions using small paired data from different modalities. The ability to mutually generate descriptions and actions is essential for robots to collaborate with humans in their daily lives, which generally requires a large dataset that maintains comprehensive pairs of both modality data. However, a paired dataset is expensive to construct and difficult to collect. To address this issue, this study proposes a two-stage training method for bidirectional translation. In the proposed method, we train recurrent autoencoders (RAEs) for descriptions and actions with a large amount of non-paired data. Then, we finetune the entire model to bind their intermediate representations using small paired data. Because the data used for pre-training do not require pairing, behavior-only data or a large language corpus can be used. We experimentally evaluated our method using a paired dataset consisting of motion-captured actions and descriptions. The results showed that our method performed well, even when the amount of paired data to train was small. The visualization of the intermediate representations of each RAE showed that similar actions were encoded in a clustered position and the corresponding feature vectors were well aligned.