# Path-Adaptive Matting for Efficient Inference Under Various Computational Cost Constraints

arXiv: https://arxiv.org/abs/2503.03228 · HTML: https://mlsanity.com/paper/2503.03228/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 31 of its 41 references that are in the map.
- First posted on arXiv 5 Mar 2025.

## Builds on (most cited first, 30 of 31)

- [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)
- [On the Variance of the Adaptive Learning Rate and Beyond](https://mlsanity.com/paper/1908.03265/) (2019)
- [Single Path One-Shot Neural Architecture Search with Uniform Sampling](https://mlsanity.com/paper/1904.00420/) (2019)
- [SkipNet: Learning Dynamic Routing in Convolutional Networks](https://mlsanity.com/paper/1711.09485/) (2017)
- [DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference](https://mlsanity.com/paper/2004.12993/) (2020)
- [BERT Loses Patience: Fast and Robust Inference with Early Exit](https://mlsanity.com/paper/2006.04152/) (2020)
- [Progressive Differentiable Architecture Search: Bridging the Depth Gap between Search and Evaluation](https://mlsanity.com/paper/1904.12760/) (2019)
- [FastBERT: a Self-distilling BERT with Adaptive Inference Time](https://mlsanity.com/paper/2004.02178/) (2020)
- [Deep Image Matting](https://mlsanity.com/paper/1703.03872/) (2017)
- [Resolution Adaptive Networks for Efficient Inference](https://mlsanity.com/paper/2003.07326/) (2020)
- [MODNet: Real-Time Trimap-Free Portrait Matting via Objective Decomposition](https://mlsanity.com/paper/2011.11961/) (2020)
- [The Right Tool for the Job: Matching Model and Instance Complexities](https://mlsanity.com/paper/2004.07453/) (2020)
- [Genetic CNN](https://mlsanity.com/paper/1703.01513/) (2017)
- [Indices Matter: Learning to Index for Deep Image Matting](https://mlsanity.com/paper/1908.00672/) (2019)
- [Dynamic Slimmable Network](https://mlsanity.com/paper/2103.13258/) (2021)
- [A Review of the Gumbel-max Trick and its Extensions for Discrete Stochasticity in Machine Learning](https://mlsanity.com/paper/2110.01515/) (2021)
- [Natural Image Matting via Guided Contextual Attention](https://mlsanity.com/paper/2001.04069/) (2020)
- [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)
- [MatteFormer: Transformer-Based Image Matting via Prior-Tokens](https://mlsanity.com/paper/2203.15662/) (2022)
- [Any-Precision Deep Neural Networks](https://mlsanity.com/paper/1911.07346/) (2019)
- [Learning Affinity-Aware Upsampling for Deep Image Matting](https://mlsanity.com/paper/2011.14288/) (2020)
- [Latency-aware Unified Dynamic Networks for Efficient Image Recognition](https://mlsanity.com/paper/2308.15949/) (2023)
- [Latency-aware Spatial-wise Dynamic Networks](https://mlsanity.com/paper/2210.06223/) (2022)
- [Boosting Robustness of Image Matting with Context Assembling and Strong Data Augmentation](https://mlsanity.com/paper/2201.06889/) (2022)
- [Noisy Differentiable Architecture Search](https://mlsanity.com/paper/2005.03566/) (2020)
- [TransMatting: Enhancing Transparent Objects Matting with Transformers](https://mlsanity.com/paper/2208.03007/) (2022)
- [Revisiting Context Aggregation for Image Matting](https://mlsanity.com/paper/2304.01171/) (2023)

## Abstract (arXiv)

In this paper, we explore a novel image matting task aimed at achieving efficient inference under various computational cost constraints, specifically FLOP limitations, using a single matting network. Existing matting methods which have not explored scalable architectures or path-learning strategies, fail to tackle this challenge. To overcome these limitations, we introduce Path-Adaptive Matting (PAM), a framework that dynamically adjusts network paths based on image contexts and computational cost constraints. We formulate the training of the computational cost-constrained matting network as a bilevel optimization problem, jointly optimizing the matting network and the path estimator. Building on this formalization, we design a path-adaptive matting architecture by incorporating path selection layers and learnable connect layers to estimate optimal paths and perform efficient inference within a unified network. Furthermore, we propose a performance-aware path-learning strategy to generate path labels online by evaluating a few paths sampled from the prior distribution of optimal paths and network estimations, enabling robust and efficient online path learning. Experiments on five image matting datasets demonstrate that the proposed PAM framework achieves competitive performance across a range of computational cost constraints.