# Boosting Robustness of Image Matting with Context Assembling and Strong Data Augmentation

arXiv: https://arxiv.org/abs/2201.06889 · HTML: https://mlsanity.com/paper/2201.06889/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 49 references that are in the map.
- First posted on arXiv 18 Jan 2022.

## Builds on (most cited first, 27 of 27)

- [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)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers](https://mlsanity.com/paper/2012.15840/) (2020)
- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [Learning to Generalize: Meta-Learning for Domain Generalization](https://mlsanity.com/paper/1710.03463/) (2017)
- [ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases](https://mlsanity.com/paper/2103.10697/) (2021)
- [Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptation](https://mlsanity.com/paper/1809.09478/) (2018)
- [BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation](https://mlsanity.com/paper/2004.02147/) (2020)
- [Real-Time High-Resolution Background Matting](https://mlsanity.com/paper/2012.07810/) (2020)
- [Deep Image Matting](https://mlsanity.com/paper/1703.03872/) (2017)
- [Robust and Generalizable Visual Representation Learning via Random Convolutions](https://mlsanity.com/paper/2007.13003/) (2020)
- [Indices Matter: Learning to Index for Deep Image Matting](https://mlsanity.com/paper/1908.00672/) (2019)
- [Mask Guided Matting via Progressive Refinement Network](https://mlsanity.com/paper/2012.06722/) (2020)
- [Context-Aware Image Matting for Simultaneous Foreground and Alpha Estimation](https://mlsanity.com/paper/1909.09725/) (2019)
- [Natural Image Matting via Guided Contextual Attention](https://mlsanity.com/paper/2001.04069/) (2020)
- [Fastformer: Additive Attention Can Be All You Need](https://mlsanity.com/paper/2108.09084/) (2021)
- [Deep Automatic Natural Image Matting](https://mlsanity.com/paper/2107.07235/) (2021)
- [Semantic Image Matting](https://mlsanity.com/paper/2104.08201/) (2021)
- [F, B, Alpha Matting](https://mlsanity.com/paper/2003.07711/) (2020)
- [Disentangled Image Matting](https://mlsanity.com/paper/1909.04686/) (2019)
- [Learning Affinity-Aware Upsampling for Deep Image Matting](https://mlsanity.com/paper/2011.14288/) (2020)
- [High-Resolution Deep Image Matting](https://mlsanity.com/paper/2009.06613/) (2020)

## Built on by (most cited first, 22 of 22)

- [ViTMatte: Boosting Image Matting with Pretrained Plain Vision Transformers](https://mlsanity.com/paper/2305.15272/) (2023)
- [Rethinking Portrait Matting with Privacy Preserving](https://mlsanity.com/paper/2203.16828/) (2022)
- [The good, the bad and the ugly sides of data augmentation: An implicit spectral regularization perspective](https://mlsanity.com/paper/2210.05021/) (2022)
- [Robust Human Matting via Semantic Guidance](https://mlsanity.com/paper/2210.05210/) (2022)
- [Deep Image Matting: A Comprehensive Survey](https://mlsanity.com/paper/2304.04672/) (2023)
- [Diffusion for Natural Image Matting](https://mlsanity.com/paper/2312.05915/) (2023)
- [Adaptive Human Matting for Dynamic Videos](https://mlsanity.com/paper/2304.06018/) (2023)
- [Revisiting Context Aggregation for Image Matting](https://mlsanity.com/paper/2304.01171/) (2023)
- [Towards Label-Efficient Human Matting: A Simple Baseline for Weakly Semi-Supervised Trimap-Free Human Matting](https://mlsanity.com/paper/2404.00921/) (2024)
- [Towards Natural Image Matting in the Wild via Real-Scenario Prior](https://mlsanity.com/paper/2410.06593/) (2024)
- [Generative Video Matting](https://mlsanity.com/paper/2508.07905/) (2025)
- [Infusing Definiteness into Randomness: Rethinking Composition Styles for Deep Image Matting](https://mlsanity.com/paper/2212.13517/) (2022)
- [Disentangled Pre-training for Image Matting](https://mlsanity.com/paper/2304.00784/) (2023)
- [Guardians of the Hair: Rescuing Soft Boundaries in Depth, Stereo, and Novel Views](https://mlsanity.com/paper/2601.03362/) (2026)
- [POBEVM: Real-time Video Matting via Progressively Optimize the Target Body and Edge](https://mlsanity.com/paper/2402.09731/) (2024)
- [DART: Depth-Enhanced Accurate and Real-Time Background Matting](https://mlsanity.com/paper/2402.15820/) (2024)
- [Dual-Context Aggregation for Universal Image Matting](https://mlsanity.com/paper/2402.18109/) (2024)
- [Learning Multiple Representations with Inconsistency-Guided Detail Regularization for Mask-Guided Matting](https://mlsanity.com/paper/2403.19213/) (2024)
- [Memory Efficient Matting with Adaptive Token Routing](https://mlsanity.com/paper/2412.10702/) (2024)
- [Path-Adaptive Matting for Efficient Inference Under Various Computational Cost Constraints](https://mlsanity.com/paper/2503.03228/) (2025)
- [Segment and Matte Anything in a Unified Model](https://mlsanity.com/paper/2601.12147/) (2026)
- [αDepth: Learning Single-Pass Soft Boundary Decomposition for Stereo Conversion](https://mlsanity.com/paper/2606.00386/) (2026)

## Abstract (arXiv)

Deep image matting methods have achieved increasingly better results on benchmarks (e.g., Composition-1k/alphamatting.com). However, the robustness, including robustness to trimaps and generalization to images from different domains, is still under-explored. Although some works propose to either refine the trimaps or adapt the algorithms to real-world images via extra data augmentation, none of them has taken both into consideration, not to mention the significant performance deterioration on benchmarks while using those data augmentation. To fill this gap, we propose an image matting method which achieves higher robustness (RMat) via multilevel context assembling and strong data augmentation targeting matting. Specifically, we first build a strong matting framework by modeling ample global information with transformer blocks in the encoder, and focusing on details in combination with convolution layers as well as a low-level feature assembling attention block in the decoder. Then, based on this strong baseline, we analyze current data augmentation and explore simple but effective strong data augmentation to boost the baseline model and contribute a more generalizable matting method. Compared with previous methods, the proposed method not only achieves state-of-the-art results on the Composition-1k benchmark (11% improvement on SAD and 27% improvement on Grad) with smaller model size, but also shows more robust generalization results on other benchmarks, on real-world images, and also on varying coarse-to-fine trimaps with our extensive experiments.