# Are We Done with Object-Centric Learning? arXiv: https://arxiv.org/abs/2504.07092 ยท HTML: https://mlsanity.com/paper/2504.07092/ ## Key facts - Cited by 11 papers in the map (data through 14 Oct 2026). - Builds on 65 of its 91 references that are in the map. - First posted on arXiv 9 Apr 2025. ## Builds on (most cited first, 30 of 65) - [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) - [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020) - [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021) - [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014) - [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023) - [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023) - [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021) - [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023) - [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016) - [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023) - [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024) - [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023) - [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016) - [Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression](https://mlsanity.com/paper/1902.09630/) (2019) - [Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift](https://mlsanity.com/paper/1906.02530/) (2019) - [Dota 2 with Large Scale Deep Reinforcement Learning](https://mlsanity.com/paper/1912.06680/) (2019) - [Object-Centric Learning with Slot Attention](https://mlsanity.com/paper/2006.15055/) (2020) - [Just Train Twice: Improving Group Robustness without Training Group Information](https://mlsanity.com/paper/2107.09044/) (2021) - [MONet: Unsupervised Scene Decomposition and Representation](https://mlsanity.com/paper/1901.11390/) (2019) - [Kubric: A scalable dataset generator](https://mlsanity.com/paper/2203.03570/) (2022) - [Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations](https://mlsanity.com/paper/2204.02937/) (2022) - [Multi-Object Representation Learning with Iterative Variational Inference](https://mlsanity.com/paper/1903.00450/) (2019) - [Noise or Signal: The Role of Image Backgrounds in Object Recognition](https://mlsanity.com/paper/2006.09994/) (2020) - [Conditional Object-Centric Learning from Video](https://mlsanity.com/paper/2111.12594/) (2021) - [On the Binding Problem in Artificial Neural Networks](https://mlsanity.com/paper/2012.05208/) (2020) - [Bridging the Gap to Real-World Object-Centric Learning](https://mlsanity.com/paper/2209.14860/) (2022) - [Deep Deterministic Uncertainty: A Simple Baseline](https://mlsanity.com/paper/2102.11582/) (2021) - [SAVi++: Towards End-to-End Object-Centric Learning from Real-World Videos](https://mlsanity.com/paper/2206.07764/) (2022) - [Alpha-CLIP: A CLIP Model Focusing on Wherever You Want](https://mlsanity.com/paper/2312.03818/) (2023) ## Built on by (most cited first, 11 of 11) - [Does Object Binding Naturally Emerge in Large Pretrained Vision Transformers?](https://mlsanity.com/paper/2510.24709/) (2025) - [Latent Particle World Models: Self-supervised Object-centric Stochastic Dynamics Modeling](https://mlsanity.com/paper/2603.04553/) (2026) - [MetaSlot: Break Through the Fixed Number of Slots in Object-Centric Learning](https://mlsanity.com/paper/2505.20772/) (2025) - [Object-level Self-Distillation for Vision Pretraining](https://mlsanity.com/paper/2506.05409/) (2025) - [Evaluating Object-Centric Models beyond Object Discovery](https://mlsanity.com/paper/2602.07532/) (2026) - [Are Object-Centric Representations Better At Compositional Generalization?](https://mlsanity.com/paper/2602.16689/) (2026) - [When Slots Compete: Slot Merging in Object-Centric Learning](https://mlsanity.com/paper/2603.11246/) (2026) - [Right Regions, Wrong Labels: Semantic Label Flips in Segmentation under Correlation Shift](https://mlsanity.com/paper/2604.13326/) (2026) - [Formalizing the Binding Problem](https://mlsanity.com/paper/2606.03976/) (2026) - [Mask-supervised Object-centric Representation Learning with LeJEPA](https://mlsanity.com/paper/2607.02404/) (2026) - [Beyond the Encoder: Object-Centric Representations Emerging from Segmentation Foundation Models](https://mlsanity.com/paper/2610.18543/) (2026) ## Abstract (arXiv) Object-centric learning (OCL) seeks to learn representations that only encode an object, isolated from other objects or background cues in a scene. This approach underpins various aims, including out-of-distribution (OOD) generalization, sample-efficient composition, and modeling of structured environments. Most research has focused on developing unsupervised mechanisms that separate objects into discrete slots in the representation space, evaluated using unsupervised object discovery. However, with recent sample-efficient segmentation models, we can separate objects in the pixel space and encode them independently. This achieves remarkable zero-shot performance on OOD object discovery benchmarks, is scalable to foundation models, and can handle a variable number of slots out-of-the-box. Hence, the goal of OCL methods to obtain object-centric representations has been largely achieved. Despite this progress, a key question remains: How does the ability to separate objects within a scene contribute to broader OCL objectives, such as OOD generalization? We address this by investigating the OOD generalization challenge caused by spurious background cues through the lens of OCL. We propose a novel, training-free probe called Object-Centric Classification with Applied Masks (OCCAM), demonstrating that segmentation-based encoding of individual objects significantly outperforms slot-based OCL methods. However, challenges in real-world applications remain. We provide the toolbox for the OCL community to use scalable object-centric representations, and focus on practical applications and fundamental questions, such as understanding object perception in human cognition. Our code is available here: https://github.com/AlexanderRubinstein/OCCAM.