# Object-Centric Action-Enhanced Representations for Robot Visuo-Motor Policy Learning

arXiv: https://arxiv.org/abs/2505.20962 · HTML: https://mlsanity.com/paper/2505.20962/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 29 references that are in the map.
- First posted on arXiv 27 May 2025.

## Builds on (most cited first, 21 of 21)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [Offline Reinforcement Learning with Implicit Q-Learning](https://mlsanity.com/paper/2110.06169/) (2021)
- [The "something something" video database for learning and evaluating visual common sense](https://mlsanity.com/paper/1706.04261/) (2017)
- [Object-Centric Learning with Slot Attention](https://mlsanity.com/paper/2006.15055/) (2020)
- [Behavioral Cloning from Observation](https://mlsanity.com/paper/1805.01954/) (2018)
- [VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training](https://mlsanity.com/paper/2210.00030/) (2022)
- [Video Instance Segmentation](https://mlsanity.com/paper/1905.04804/) (2019)
- [RoboNet: Large-Scale Multi-Robot Learning](https://mlsanity.com/paper/1910.11215/) (2019)
- [VIOLA: Imitation Learning for Vision-Based Manipulation with Object Proposal Priors](https://mlsanity.com/paper/2210.11339/) (2022)
- [Invariant Slot Attention: Object Discovery with Slot-Centric Reference Frames](https://mlsanity.com/paper/2302.04973/) (2023)
- [Self-supervised Object-Centric Learning for Videos](https://mlsanity.com/paper/2310.06907/) (2023)
- [Train Offline, Test Online: A Real Robot Learning Benchmark](https://mlsanity.com/paper/2306.00942/) (2023)
- [DynaMo: In-Domain Dynamics Pretraining for Visuo-Motor Control](https://mlsanity.com/paper/2409.12192/) (2024)
- [Learning to Navigate Using Mid-Level Visual Priors](https://mlsanity.com/paper/1912.11121/) (2019)
- [Composing Pre-Trained Object-Centric Representations for Robotics From "What" and "Where" Foundation Models](https://mlsanity.com/paper/2404.13474/) (2024)
- [Building an Affordances Map with Interactive Perception](https://mlsanity.com/paper/1903.04413/) (2019)

## Abstract (arXiv)

Learning visual representations from observing actions to benefit robot visuo-motor policy generation is a promising direction that closely resembles human cognitive function and perception. Motivated by this, and further inspired by psychological theories suggesting that humans process scenes in an object-based fashion, we propose an object-centric encoder that performs semantic segmentation and visual representation generation in a coupled manner, unlike other works, which treat these as separate processes. To achieve this, we leverage the Slot Attention mechanism and use the SOLV model, pretrained in large out-of-domain datasets, to bootstrap fine-tuning on human action video data. Through simulated robotic tasks, we demonstrate that visual representations can enhance reinforcement and imitation learning training, highlighting the effectiveness of our integrated approach for semantic segmentation and encoding. Furthermore, we show that exploiting models pretrained on out-of-domain datasets can benefit this process, and that fine-tuning on datasets depicting human actions -- although still out-of-domain -- , can significantly improve performance due to close alignment with robotic tasks. These findings show the capability to reduce reliance on annotated or robot-specific action datasets and the potential to build on existing visual encoders to accelerate training and improve generalizability.