# Compositional Convolutional Neural Networks: A Robust and Interpretable Model for Object Recognition under Occlusion

arXiv: https://arxiv.org/abs/2006.15538 · HTML: https://mlsanity.com/paper/2006.15538/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Jun 2020.

## Built on by (most cited first, 30 of 38)

- [MOSE: A New Dataset for Video Object Segmentation in Complex Scenes](https://mlsanity.com/paper/2302.01872/) (2023)
- [Occluded Video Instance Segmentation: A Benchmark](https://mlsanity.com/paper/2102.01558/) (2021)
- [MOSEv2: A More Challenging Dataset for Video Object Segmentation in Complex Scenes](https://mlsanity.com/paper/2508.05630/) (2025)
- [OOD-CV: A Benchmark for Robustness to Out-of-Distribution Shifts of Individual Nuisances in Natural Images](https://mlsanity.com/paper/2111.14341/) (2021)
- [NeMo: Neural Mesh Models of Contrastive Features for Robust 3D Pose Estimation](https://mlsanity.com/paper/2101.12378/) (2021)
- [SwapMix: Diagnosing and Regularizing the Over-Reliance on Visual Context in Visual Question Answering](https://mlsanity.com/paper/2204.02285/) (2022)
- [3D-Aware Neural Body Fitting for Occlusion Robust 3D Human Pose Estimation](https://mlsanity.com/paper/2308.10123/) (2023)
- [Occlusion Handling in Generic Object Detection: A Review](https://mlsanity.com/paper/2101.08845/) (2021)
- [Robust Category-Level 6D Pose Estimation with Coarse-to-Fine Rendering of Neural Features](https://mlsanity.com/paper/2209.05624/) (2022)
- [Learning Environment-Aware Affordance for 3D Articulated Object Manipulation under Occlusions](https://mlsanity.com/paper/2309.07510/) (2023)
- [Social Fabric: Tubelet Compositions for Video Relation Detection](https://mlsanity.com/paper/2108.08363/) (2021)
- [Adversarial Patch Attacks and Defences in Vision-Based Tasks: A Survey](https://mlsanity.com/paper/2206.08304/) (2022)
- [Neural View Synthesis and Matching for Semi-Supervised Few-Shot Learning of 3D Pose](https://mlsanity.com/paper/2110.14213/) (2021)
- [OOD-CV-v2: An extended Benchmark for Robustness to Out-of-Distribution Shifts of Individual Nuisances in Natural Images](https://mlsanity.com/paper/2304.10266/) (2023)
- [Low-resolution Human Pose Estimation](https://mlsanity.com/paper/2109.09090/) (2021)
- [iNeMo: Incremental Neural Mesh Models for Robust Class-Incremental Learning](https://mlsanity.com/paper/2407.09271/) (2024)
- [A.I. Robustness: a Human-Centered Perspective on Technological Challenges and Opportunities](https://mlsanity.com/paper/2210.08906/) (2022)
- [BLADE: Box-Level Supervised Amodal Segmentation through Directed Expansion](https://mlsanity.com/paper/2401.01642/) (2024)
- [Review of Demographic Fairness in Face Recognition](https://mlsanity.com/paper/2502.02309/) (2025)
- [Occluded Video Instance Segmentation: Dataset and ICCV 2021 Challenge](https://mlsanity.com/paper/2111.07950/) (2021)
- [OccRob: Efficient SMT-Based Occlusion Robustness Verification of Deep Neural Networks](https://mlsanity.com/paper/2301.11912/) (2023)
- [CORL: Compositional Representation Learning for Few-Shot Classification](https://mlsanity.com/paper/2101.11878/) (2021)
- [Blocks World Revisited: The Effect of Self-Occlusion on Classification by Convolutional Neural Networks](https://mlsanity.com/paper/2102.12911/) (2021)
- [Neural Textured Deformable Meshes for Robust Analysis-by-Synthesis](https://mlsanity.com/paper/2306.00118/) (2023)
- [PLUG: Revisiting Amodal Segmentation with Foundation Model and Hierarchical Focus](https://mlsanity.com/paper/2405.16094/) (2024)
- [A Bayesian Approach to OOD Robustness in Image Classification](https://mlsanity.com/paper/2403.07277/) (2024)
- [COCO-OLAC: A Benchmark for Occluded Panoptic Segmentation and Image Understanding](https://mlsanity.com/paper/2409.12760/) (2024)
- [Now You See Me: Robust approach to Partial Occlusions](https://mlsanity.com/paper/2304.11779/) (2023)
- [A Light-weight Interpretable Compositional Model for Nuclei Detection and Weakly-Supervised Segmentation](https://mlsanity.com/paper/2110.13846/) (2021)
- [Latent Enhancing AutoEncoder for Occluded Image Classification](https://mlsanity.com/paper/2402.06936/) (2024)

## Abstract (arXiv)

Computer vision systems in real-world applications need to be robust to partial occlusion while also being explainable. In this work, we show that black-box deep convolutional neural networks (DCNNs) have only limited robustness to partial occlusion. We overcome these limitations by unifying DCNNs with part-based models into Compositional Convolutional Neural Networks (CompositionalNets) - an interpretable deep architecture with innate robustness to partial occlusion. Specifically, we propose to replace the fully connected classification head of DCNNs with a differentiable compositional model that can be trained end-to-end. The structure of the compositional model enables CompositionalNets to decompose images into objects and context, as well as to further decompose object representations in terms of individual parts and the objects' pose. The generative nature of our compositional model enables it to localize occluders and to recognize objects based on their non-occluded parts. We conduct extensive experiments in terms of image classification and object detection on images of artificially occluded objects from the PASCAL3D+ and ImageNet dataset, and real images of partially occluded vehicles from the MS-COCO dataset. Our experiments show that CompositionalNets made from several popular DCNN backbones (VGG-16, ResNet50, ResNext) improve by a large margin over their non-compositional counterparts at classifying and detecting partially occluded objects. Furthermore, they can localize occluders accurately despite being trained with class-level supervision only. Finally, we demonstrate that CompositionalNets provide human interpretable predictions as their individual components can be understood as detecting parts and estimating an objects' viewpoint.