# Reinforcement Learning as a Parsimonious Alternative to Prediction Cascades: A Case Study on Image Segmentation

arXiv: https://arxiv.org/abs/2402.11760 · HTML: https://mlsanity.com/paper/2402.11760/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RL with diffusion and flow models, one of 15 directions in Deep reinforcement learning methods.
- Builds on 20 of its 31 references that are in the map.
- First posted on arXiv 19 Feb 2024.

## Placed in

- Deep reinforcement learning methods / [RL with diffusion and flow models](https://mlsanity.com/deeprl/rl-with-diffusion-and-flow-models/)

## Builds on (most cited first, 20 of 20)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [Knowledge Distillation: A Survey](https://mlsanity.com/paper/2006.05525/) (2020)
- [Towards Understanding Knowledge Distillation](https://mlsanity.com/paper/2105.13093/) (2021)
- [Comparing Kullback-Leibler Divergence and Mean Squared Error Loss in Knowledge Distillation](https://mlsanity.com/paper/2105.08919/) (2021)
- [Deep Learning for IoT Big Data and Streaming Analytics: A Survey](https://mlsanity.com/paper/1712.04301/) (2017)
- [IDK Cascades: Fast Deep Learning by Learning not to Overthink](https://mlsanity.com/paper/1706.00885/) (2017)
- [Learning When and Where to Zoom with Deep Reinforcement Learning](https://mlsanity.com/paper/2003.00425/) (2020)
- [EfficientViT: Multi-Scale Linear Attention for High-Resolution Dense Prediction](https://mlsanity.com/paper/2205.14756/) (2022)
- [Machine Learning in IoT Security: Current Solutions and Future Challenges](https://mlsanity.com/paper/1904.05735/) (2019)
- [Efficient Object Detection in Large Images using Deep Reinforcement Learning](https://mlsanity.com/paper/1912.03966/) (2019)
- [Learning Complexity-Aware Cascades for Deep Pedestrian Detection](https://mlsanity.com/paper/1507.05348/) (2015)
- [How to Manage Tiny Machine Learning at Scale: An Industrial Perspective](https://mlsanity.com/paper/2202.09113/) (2022)

## Abstract (arXiv)

Deep learning architectures have achieved state-of-the-art (SOTA) performance on computer vision tasks such as object detection and image segmentation. This may be attributed to the use of over-parameterized, monolithic deep learning architectures executed on large datasets. Although such architectures lead to increased accuracy, this is usually accompanied by a large increase in computation and memory requirements during inference. While this is a non-issue in traditional machine learning pipelines, the recent confluence of machine learning and fields like the Internet of Things has rendered such large architectures infeasible for execution in low-resource settings. In such settings, previous efforts have proposed decision cascades where inputs are passed through models of increasing complexity until desired performance is achieved. However, we argue that cascaded prediction leads to increased computational cost due to wasteful intermediate computations. To address this, we propose PaSeR (Parsimonious Segmentation with Reinforcement Learning) a non-cascading, cost-aware learning pipeline as an alternative to cascaded architectures. Through experimental evaluation on real-world and standard datasets, we demonstrate that PaSeR achieves better accuracy while minimizing computational cost relative to cascaded models. Further, we introduce a new metric IoU/GigaFlop to evaluate the balance between cost and performance. On the real-world task of battery material phase segmentation, PaSeR yields a minimum performance improvement of 174% on the IoU/GigaFlop metric with respect to baselines. We also demonstrate PaSeR's adaptability to complementary models trained on a noisy MNIST dataset, where it achieved a minimum performance improvement on IoU/GigaFlop of 13.4% over SOTA models. Code and data are available at https://github.com/scailab/paser .