# Deeply Cascaded U-Net for Multi-Task Image Processing

Source: [Deeply Cascaded U-Net for Multi-Task Image Processing](<https://www.sota2.com/research/paper/68fa67761e209131cea167e3>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T22:15:13.389Z

Authors: Ilja Gubins, Remco C. Veltkamp

Published: 2020-05-01T05:06:35.000Z

## Abstract

In current practice, many image processing tasks are done sequentially (e.g. denoising, dehazing, followed by semantic segmentation). In this paper, we propose a novel multi-task neural network architecture designed for combining sequential image processing tasks. We extend U-Net by additional decoding pathways for each individual task, and explore deep cascading of outputs and connectivity from one pathway to another. We demonstrate effectiveness of the proposed approach on denoising and semantic segmentation, as well as on progressive coarse-to-fine semantic segmentation, and achieve better performance than multiple individual or jointly-trained networks, with lower number of trainable parameters.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2005.00225>)

[PDF](<https://arxiv.org/pdf/2005.00225.pdf>)