Lossless Adaptation of Pretrained Vision Models For Robotic Manipulation

Recent works have shown that large models pretrained on common visual learning tasks can provide useful representations for a wide range of specialized perception problems, as well as a variety of robotic manipulation tasks. While prior work on robotic manipulation has predominantly used frozen pretrained features, we demonstrate that in robotics this approach can fail to reach optimal performance, and that fine-tuning of the full model can lead to significantly better results. We introduce lossless adaptation to address this shortcoming of classical fine-tuning. We demonstrate that appropriate placement of our parameter efficient adapters can significantly reduce the performance gap between frozen pretrained representations and full end-to-end finetuning without changes to the original representation and thus preserving original capabilities of the pretrained model. We perform a comprehensive investigation across three major model architectures (ViTs, NFNets, and ResNets), supervised (ImageNet-1K classification) and self-supervised pretrained weights (CLIP, BYOL, Visual MAE) in 3 task domains and 35 individual tasks, and demonstrate that our claims are strongly validated in various settings. Please see real world videos at https://sites.google.com/view/robo-adapters. Pretrained general-purpose vision models, often also referred to as vision foundation models (Yuan et al., 2021), have developed a growing set of perceptual capabilities in recent years. Large-scale vision-language models such as CLIP (Radford et al., 2021) and ALIGN (Jia et al., 2021)) are examples of these highly capable general-purpose vision models which have enabled many applications for image generation/editing (Ramesh et al., 2022; Saharia et al.) and image-based dialog (Alayrac et al., 2022). Existing self-supervised pretrained visual models, such as SimCLR (Chen et al., 2020), BYOL (Grill et al., 2020) or Visual MAE (He et al., 2022), have also been shown to provide strong initializations for a wide range of visual downstream tasks. How can we unlock the power of these models for increasingly novel and challenging control applications? One solution is to add an output head for each control task and fine-tune the entire architecture. However, fine-tuning degrades performance on the original task(s) the model was trained for, and therefore requires maintaining copies of the model for all tasks we wish to concurrently support. This strategy quickly becomes infeasible as we move towards more general and multi-task agents. For instance, embodied agents acting in the real world will end up solving thousands of downstream manipulation tasks. Given limited hardware capabilities of robots keeping separate copies of increasingly large models (e.g. This is further exacerbated for robot manipulation wherein hardware and tool differences can result in different task configurations which may require different representations.