What explains the success of cross-modal fine-tuning with ORCA? ...
ORCA (Shen et al., 2023) is a recent technique for cross-modal fine-tuning, i.e., applying pre-trained transformer models to modalities beyond their training data. The technique consists primarily of training an embedder and fine-tuning the embedder and model. Despite its high performance on a varie...
| Main Authors: | , , , , |
|---|---|
| Format: | Article in Journal/Newspaper |
| Language: | unknown |
| Published: |
arXiv
2024
|
| Subjects: | |
| Online Access: | https://dx.doi.org/10.48550/arxiv.2403.13537 https://arxiv.org/abs/2403.13537 |
| Summary: | ORCA (Shen et al., 2023) is a recent technique for cross-modal fine-tuning, i.e., applying pre-trained transformer models to modalities beyond their training data. The technique consists primarily of training an embedder and fine-tuning the embedder and model. Despite its high performance on a variety of downstream tasks, we do not understand precisely how each of these components contribute to ORCA's success. Therefore, we run a series of ablations and find that embedder training does not help 2D tasks at all, contrary to what the original paper posits. In 1D tasks, some amount of embedder training is necessary but more is not better. In 4 out of 6 datasets we experiment with, it is model fine-tuning that makes the biggest difference. Through our ablations and baselines, we contribute a better understanding of the individual components of ORCA. ... |
|---|