# Amodal Segmentation through Out-of-Task and Out-of-Distribution Generalization with a Bayesian Model

arXiv: https://arxiv.org/abs/2010.13175 · HTML: https://mlsanity.com/paper/2010.13175/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Oct 2020.

## Built on by (most cited first, 29 of 29)

- [Segmenting Moving Objects via an Object-Centric Layered Representation](https://mlsanity.com/paper/2207.02206/) (2022)
- [Amodal Ground Truth and Completion in the Wild](https://mlsanity.com/paper/2312.17247/) (2023)
- [AISFormer: Amodal Instance Segmentation with Transformer](https://mlsanity.com/paper/2210.06323/) (2022)
- [Coarse-to-Fine Amodal Segmentation with Shape Prior](https://mlsanity.com/paper/2308.16825/) (2023)
- [A Tri-Layer Plugin to Improve Occluded Detection](https://mlsanity.com/paper/2210.10046/) (2022)
- [Fixing Overconfidence in Dynamic Neural Networks](https://mlsanity.com/paper/2302.06359/) (2023)
- [Image Amodal Completion: A Survey](https://mlsanity.com/paper/2207.02062/) (2022)
- [Object-level Scene Deocclusion](https://mlsanity.com/paper/2406.07706/) (2024)
- [Self-supervised Amodal Video Object Segmentation](https://mlsanity.com/paper/2210.12733/) (2022)
- [Uncertainty Quantification via Stable Distribution Propagation](https://mlsanity.com/paper/2402.08324/) (2024)
- [Rethinking Amodal Video Segmentation from Learning Supervised Signals with Object-centric Representation](https://mlsanity.com/paper/2309.13248/) (2023)
- [BLADE: Box-Level Supervised Amodal Segmentation through Directed Expansion](https://mlsanity.com/paper/2401.01642/) (2024)
- [Masked Autoencoding Does Not Help Natural Language Supervision at Scale](https://mlsanity.com/paper/2301.07836/) (2023)
- [Occlusion-Aware Seamless Segmentation](https://mlsanity.com/paper/2407.02182/) (2024)
- [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)
- [Your Classifier Can Be Secretly a Likelihood-Based OOD Detector](https://mlsanity.com/paper/2408.04851/) (2024)
- [Believing is Seeing: Unobserved Object Detection using Generative Models](https://mlsanity.com/paper/2410.05869/) (2024)
- [Unlocking Constraints: Source-Free Occlusion-Aware Seamless Segmentation](https://mlsanity.com/paper/2506.21198/) (2025)
- [Unveiling the Invisible: Reasoning Complex Occlusions Amodally with AURA](https://mlsanity.com/paper/2503.10225/) (2025)
- [Sequential Amodal Segmentation via Cumulative Occlusion Learning](https://mlsanity.com/paper/2405.05791/) (2024)
- [Hyper-Transformer for Amodal Completion](https://mlsanity.com/paper/2405.19949/) (2024)
- [Foundation Models for Amodal Video Instance Segmentation in Automated Driving](https://mlsanity.com/paper/2409.14095/) (2024)
- [Contact-Aware Amodal Completion for Human-Object Interaction via Multi-Regional Inpainting](https://mlsanity.com/paper/2508.00427/) (2025)
- [Shape Distribution Matters: Shape-specific Mixture-of-Experts for Amodal Segmentation under Diverse Occlusions](https://mlsanity.com/paper/2508.01664/) (2025)
- [Stable Diffusion-Based Approach for Human De-Occlusion](https://mlsanity.com/paper/2508.12663/) (2025)
- [Learnable Shape Prototypes with Occlusion-Geometry-Guided Injection for Amodal Instance Segmentation](https://mlsanity.com/paper/2605.24533/) (2026)
- [Amodal Segmentation for Laparoscopic Surgery Video Instruments](https://mlsanity.com/paper/2408.01067/) (2024)
- [A Bilayer Segmentation-Recombination Network for Accurate Segmentation of Overlapping C. elegans](https://mlsanity.com/paper/2411.17557/) (2024)

## Abstract (arXiv)

Amodal completion is a visual task that humans perform easily but which is difficult for computer vision algorithms. The aim is to segment those object boundaries which are occluded and hence invisible. This task is particularly challenging for deep neural networks because data is difficult to obtain and annotate. Therefore, we formulate amodal segmentation as an out-of-task and out-of-distribution generalization problem. Specifically, we replace the fully connected classifier in neural networks with a Bayesian generative model of the neural network features. The model is trained from non-occluded images using bounding box annotations and class labels only, but is applied to generalize out-of-task to object segmentation and to generalize out-of-distribution to segment occluded objects. We demonstrate how such Bayesian models can naturally generalize beyond the training task labels when they learn a prior that models the object's background context and shape. Moreover, by leveraging an outlier process, Bayesian models can further generalize out-of-distribution to segment partially occluded objects and to predict their amodal object boundaries. Our algorithm outperforms alternative methods that use the same supervision by a large margin, and even outperforms methods where annotated amodal segmentations are used during training, when the amount of occlusion is large. Code is publicly available at https://github.com/YihongSun/Bayesian-Amodal.