# Revisiting Context Aggregation for Image Matting

arXiv: https://arxiv.org/abs/2304.01171 · HTML: https://mlsanity.com/paper/2304.01171/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 49 references that are in the map.
- First posted on arXiv 3 Apr 2023.

## Builds on (most cited first, 26 of 26)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [Group Normalization](https://mlsanity.com/paper/1803.08494/) (2018)
- [On the Variance of the Adaptive Learning Rate and Beyond](https://mlsanity.com/paper/1908.03265/) (2019)
- [Understanding the Effective Receptive Field in Deep Convolutional Neural Networks](https://mlsanity.com/paper/1701.04128/) (2017)
- [Deep Image Matting](https://mlsanity.com/paper/1703.03872/) (2017)
- [Bridging Composite and Real: Towards End-to-end Deep Image Matting](https://mlsanity.com/paper/2010.16188/) (2020)
- [Mask Guided Matting via Progressive Refinement Network](https://mlsanity.com/paper/2012.06722/) (2020)
- [Natural Image Matting via Guided Contextual Attention](https://mlsanity.com/paper/2001.04069/) (2020)
- [Semantic Human Matting](https://mlsanity.com/paper/1809.01354/) (2018)
- [Privacy-Preserving Portrait Matting](https://mlsanity.com/paper/2104.14222/) (2021)
- [Deep Automatic Natural Image Matting](https://mlsanity.com/paper/2107.07235/) (2021)
- [Semantic Image Matting](https://mlsanity.com/paper/2104.08201/) (2021)
- [MatteFormer: Transformer-Based Image Matting via Prior-Tokens](https://mlsanity.com/paper/2203.15662/) (2022)
- [Micro-Batch Training with Batch-Channel Normalization and Weight Standardization](https://mlsanity.com/paper/1903.10520/) (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)
- [Boosting Robustness of Image Matting with Context Assembling and Strong Data Augmentation](https://mlsanity.com/paper/2201.06889/) (2022)
- [TransMatting: Enhancing Transparent Objects Matting with Transformers](https://mlsanity.com/paper/2208.03007/) (2022)
- [Long-Range Feature Propagating for Natural Image Matting](https://mlsanity.com/paper/2109.12252/) (2021)
- [Cascade Image Matting with Deformable Graph Refinement](https://mlsanity.com/paper/2105.02646/) (2021)
- [Hierarchical and Progressive Image Matting](https://mlsanity.com/paper/2210.06906/) (2022)

## Built on by (most cited first, 5 of 5)

- [Matte Anything: Interactive Natural Image Matting with Segment Anything Models](https://mlsanity.com/paper/2306.04121/) (2023)
- [Diffusion for Natural Image Matting](https://mlsanity.com/paper/2312.05915/) (2023)
- [Learning Trimaps via Clicks for Image Matting](https://mlsanity.com/paper/2404.00335/) (2024)
- [Enhancing Image Matting in Real-World Scenes with Mask-Guided Iterative Refinement](https://mlsanity.com/paper/2502.17093/) (2025)
- [Path-Adaptive Matting for Efficient Inference Under Various Computational Cost Constraints](https://mlsanity.com/paper/2503.03228/) (2025)

## Abstract (arXiv)

Traditional studies emphasize the significance of context information in improving matting performance. Consequently, deep learning-based matting methods delve into designing pooling or affinity-based context aggregation modules to achieve superior results. However, these modules cannot well handle the context scale shift caused by the difference in image size during training and inference, resulting in matting performance degradation. In this paper, we revisit the context aggregation mechanisms of matting networks and find that a basic encoder-decoder network without any context aggregation modules can actually learn more universal context aggregation, thereby achieving higher matting performance compared to existing methods. Building on this insight, we present AEMatter, a matting network that is straightforward yet very effective. AEMatter adopts a Hybrid-Transformer backbone with appearance-enhanced axis-wise learning (AEAL) blocks to build a basic network with strong context aggregation learning capability. Furthermore, AEMatter leverages a large image training strategy to assist the network in learning context aggregation from data. Extensive experiments on five popular matting datasets demonstrate that the proposed AEMatter outperforms state-of-the-art matting methods by a large margin.