# RobustCLEVR: A Benchmark and Framework for Evaluating Robustness in Object-centric Learning

arXiv: https://arxiv.org/abs/2308.14899 · HTML: https://mlsanity.com/paper/2308.14899/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 46 of its 55 references that are in the map.
- First posted on arXiv 28 Aug 2023.

## Builds on (most cited first, 30 of 46)

- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning](https://mlsanity.com/paper/1612.06890/) (2016)
- [AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty](https://mlsanity.com/paper/1912.02781/) (2019)
- [Object-Centric Learning with Slot Attention](https://mlsanity.com/paper/2006.15055/) (2020)
- [GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields](https://mlsanity.com/paper/2011.12100/) (2020)
- [Measuring Robustness to Natural Distribution Shifts in Image Classification](https://mlsanity.com/paper/2007.00644/) (2020)
- [MONet: Unsupervised Scene Decomposition and Representation](https://mlsanity.com/paper/1901.11390/) (2019)
- [Multi-Object Representation Learning with Iterative Variational Inference](https://mlsanity.com/paper/1903.00450/) (2019)
- [Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming](https://mlsanity.com/paper/1907.07484/) (2019)
- [Conditional Object-Centric Learning from Video](https://mlsanity.com/paper/2111.12594/) (2021)
- [Attend, Infer, Repeat: Fast Scene Understanding with Generative Models](https://mlsanity.com/paper/1603.08575/) (2016)
- [Towards Causal Representation Learning](https://mlsanity.com/paper/2102.11107/) (2021)
- [Causality matters in medical imaging](https://mlsanity.com/paper/1912.08142/) (2019)
- [SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decomposition](https://mlsanity.com/paper/2001.02407/) (2020)
- [Simple Unsupervised Object-Centric Learning for Complex and Naturalistic Videos](https://mlsanity.com/paper/2205.14065/) (2022)
- [Sequential Attend, Infer, Repeat: Generative Modelling of Moving Objects](https://mlsanity.com/paper/1806.01794/) (2018)
- [3D Common Corruptions and Data Augmentation](https://mlsanity.com/paper/2203.01441/) (2022)
- [Benchmarking Robustness of 3D Object Detection to Common Corruptions in Autonomous Driving](https://mlsanity.com/paper/2303.11040/) (2023)
- [GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement](https://mlsanity.com/paper/2104.09958/) (2021)
- [On Robustness and Transferability of Convolutional Neural Networks](https://mlsanity.com/paper/2007.08558/) (2020)
- [ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi-Object Segmentation](https://mlsanity.com/paper/2111.10265/) (2021)
- [Generalization and Robustness Implications in Object-Centric Learning](https://mlsanity.com/paper/2107.00637/) (2021)
- [Discovering Causal Signals in Images](https://mlsanity.com/paper/1605.08179/) (2016)
- [Visual Causal Feature Learning](https://mlsanity.com/paper/1412.2309/) (2014)
- [Do Image Classifiers Generalize Across Time?](https://mlsanity.com/paper/1906.02168/) (2019)
- [Generative Neurosymbolic Machines](https://mlsanity.com/paper/2010.12152/) (2020)
- [A Comprehensive Study of Image Classification Model Sensitivity to Foregrounds, Backgrounds, and Visual Attributes](https://mlsanity.com/paper/2201.10766/) (2022)

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

- [RobustSpring: Benchmarking Robustness to Image Corruptions for Optical Flow, Scene Flow and Stereo](https://mlsanity.com/paper/2505.09368/) (2025)
- [Towards Virtual Clinical Trials of Radiology AI with Conditional Generative Modeling](https://mlsanity.com/paper/2502.09688/) (2025)
- [Metamorphic Testing for Pose Estimation Systems](https://mlsanity.com/paper/2502.09460/) (2025)
- [Causality-Driven Audits of Model Robustness](https://mlsanity.com/paper/2410.23494/) (2024)
- [A Causal Framework for Aligning Image Quality Metrics and Deep Neural Network Robustness](https://mlsanity.com/paper/2503.02797/) (2025)
- [Are Object-Centric Representations Better At Compositional Generalization?](https://mlsanity.com/paper/2602.16689/) (2026)

## Abstract (arXiv)

Object-centric representation learning offers the potential to overcome limitations of image-level representations by explicitly parsing image scenes into their constituent components. While image-level representations typically lack robustness to natural image corruptions, the robustness of object-centric methods remains largely untested. To address this gap, we present the RobustCLEVR benchmark dataset and evaluation framework. Our framework takes a novel approach to evaluating robustness by enabling the specification of causal dependencies in the image generation process grounded in expert knowledge and capable of producing a wide range of image corruptions unattainable in existing robustness evaluations. Using our framework, we define several causal models of the image corruption process which explicitly encode assumptions about the causal relationships and distributions of each corruption type. We generate dataset variants for each causal model on which we evaluate state-of-the-art object-centric methods. Overall, we find that object-centric methods are not inherently robust to image corruptions. Our causal evaluation approach exposes model sensitivities not observed using conventional evaluation processes, yielding greater insight into robustness differences across algorithms. Lastly, while conventional robustness evaluations view corruptions as out-of-distribution, we use our causal framework to show that even training on in-distribution image corruptions does not guarantee increased model robustness. This work provides a step towards more concrete and substantiated understanding of model performance and deterioration under complex corruption processes of the real-world.