# Cascade Decoder: A Universal Decoding Method for Biomedical Image Segmentation

arXiv: https://arxiv.org/abs/1901.04949 · HTML: https://mlsanity.com/paper/1901.04949/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Jan 2019.

## Built on by (most cited first, 4 of 4)

- [Hierarchical Self-Supervised Learning for Medical Image Segmentation Based on Multi-Domain Data Aggregation](https://mlsanity.com/paper/2107.04886/) (2021)
- [Cell Instance Segmentation: The Devil Is in the Boundaries](https://mlsanity.com/paper/2510.09848/) (2025)
- [H-EMD: A Hierarchical Earth Mover's Distance Method for Instance Segmentation](https://mlsanity.com/paper/2206.01309/) (2022)
- [Making Language Model a Hierarchical Classifier](https://mlsanity.com/paper/2507.12930/) (2025)

## Abstract (arXiv)

The Encoder-Decoder architecture is a main stream deep learning model for biomedical image segmentation. The encoder fully compresses the input and generates encoded features, and the decoder then produces dense predictions using encoded features. However, decoders are still under-explored in such architectures. In this paper, we comprehensively study the state-of-the-art Encoder-Decoder architectures, and propose a new universal decoder, called cascade decoder, to improve semantic segmentation accuracy. Our cascade decoder can be embedded into existing networks and trained altogether in an end-to-end fashion. The cascade decoder structure aims to conduct more effective decoding of hierarchically encoded features and is more compatible with common encoders than the known decoders. We replace the decoders of state-of-the-art models with our cascade decoder for several challenging biomedical image segmentation tasks, and the considerable improvements achieved demonstrate the efficacy of our new decoding method.