# Object-Centric Pretraining via Target Encoder Bootstrapping

arXiv: https://arxiv.org/abs/2503.15141 · HTML: https://mlsanity.com/paper/2503.15141/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Self-improving MLLMs and synthetic data, one of 13 directions in Synthetic data and self-improvement for LLMs.
- Builds on 30 of its 33 references that are in the map.
- First posted on arXiv 19 Mar 2025.

## Placed in

- Synthetic data and self-improvement for LLMs / [Self-improving MLLMs and synthetic data](https://mlsanity.com/synth/self-improving-mllms-and-synthetic-data/)

## Builds on (most cited first, 30 of 30)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [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)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2301.08243/) (2023)
- [iBOT: Image BERT Pre-Training with Online Tokenizer](https://mlsanity.com/paper/2111.07832/) (2021)
- [Object-Centric Learning with Slot Attention](https://mlsanity.com/paper/2006.15055/) (2020)
- [Bridging the Gap to Real-World Object-Centric Learning](https://mlsanity.com/paper/2209.14860/) (2022)
- [Illiterate DALL-E Learns to Compose](https://mlsanity.com/paper/2110.11405/) (2021)
- [ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi-Object Segmentation](https://mlsanity.com/paper/2111.10265/) (2021)
- [Object Scene Representation Transformer](https://mlsanity.com/paper/2206.06922/) (2022)
- [Object-Centric Slot Diffusion](https://mlsanity.com/paper/2303.10834/) (2023)
- [SlotDiffusion: Object-Centric Generative Modeling with Diffusion Models](https://mlsanity.com/paper/2305.11281/) (2023)
- [Self-Supervised Visual Representation Learning with Semantic Grouping](https://mlsanity.com/paper/2205.15288/) (2022)
- [SPOT: Self-Training with Patch-Order Permutation for Object-Centric Learning with Autoregressive Transformers](https://mlsanity.com/paper/2312.00648/) (2023)
- [Towards In-context Scene Understanding](https://mlsanity.com/paper/2306.01667/) (2023)
- [Self-supervised Visual Reinforcement Learning with Object-centric Representations](https://mlsanity.com/paper/2011.14381/) (2020)
- [Provable Compositional Generalization for Object-Centric Learning](https://mlsanity.com/paper/2310.05327/) (2023)
- [Entity-Centric Reinforcement Learning for Object Manipulation from Pixels](https://mlsanity.com/paper/2404.01220/) (2024)
- [Capturing the objects of vision with neural networks](https://mlsanity.com/paper/2109.03351/) (2021)
- [CrOC: Cross-View Online Clustering for Dense Visual Representation Learning](https://mlsanity.com/paper/2303.13245/) (2023)
- [CrIBo: Self-Supervised Learning via Cross-Image Object-Level Bootstrapping](https://mlsanity.com/paper/2310.07855/) (2023)
- [Slot-VLM: SlowFast Slots for Video-Language Modeling](https://mlsanity.com/paper/2402.13088/) (2024)

## Built on by (most cited first, 6 of 6)

- [Causal-JEPA: Learning World Models through Object-Level Latent Masking](https://mlsanity.com/paper/2602.11389/) (2026)
- [Latent Particle World Models: Self-supervised Object-centric Stochastic Dynamics Modeling](https://mlsanity.com/paper/2603.04553/) (2026)
- [ContextFusion and Bootstrap: An Effective Approach to Improve Slot Attention-Based Object-Centric Learning](https://mlsanity.com/paper/2509.02032/) (2025)
- [VINO: Video-driven Invariance for Non-contextual Objects via Structural Prior Guided De-contextualization](https://mlsanity.com/paper/2603.07222/) (2026)
- [Information theoretic underpinning of self-supervised learning by clustering](https://mlsanity.com/paper/2605.11870/) (2026)
- [Mask-supervised Object-centric Representation Learning with LeJEPA](https://mlsanity.com/paper/2607.02404/) (2026)

## Abstract (arXiv)

Object-centric representation learning has recently been successfully applied to real-world datasets. This success can be attributed to pretrained non-object-centric foundation models, whose features serve as reconstruction targets for slot attention. However, targets must remain frozen throughout the training, which sets an upper bound on the performance object-centric models can attain. Attempts to update the target encoder by bootstrapping result in large performance drops, which can be attributed to its lack of object-centric inductive biases, causing the object-centric model's encoder to drift away from representations useful as reconstruction targets. To address these limitations, we propose Object-CEntric Pretraining by Target Encoder BOotstrapping, a self-distillation setup for training object-centric models from scratch, on real-world data, for the first time ever. In OCEBO, the target encoder is updated as an exponential moving average of the object-centric model, thus explicitly being enriched with object-centric inductive biases introduced by slot attention while removing the upper bound on performance present in other models. We mitigate the slot collapse caused by random initialization of the target encoder by introducing a novel cross-view patch filtering approach that limits the supervision to sufficiently informative patches. When pretrained on 241k images from COCO, OCEBO achieves unsupervised object discovery performance comparable to that of object-centric models with frozen non-object-centric target encoders pretrained on hundreds of millions of images. The code and pretrained models are publicly available at https://github.com/djukicn/ocebo.