# Conditional Reconstruction for Open-set Semantic Segmentation

arXiv: https://arxiv.org/abs/2203.01368 · HTML: https://mlsanity.com/paper/2203.01368/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 13 references that are in the map.
- First posted on arXiv 2 Mar 2022.

## Builds on (most cited first, 9 of 9)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Towards Open Set Deep Networks](https://mlsanity.com/paper/1511.06233/) (2015)
- [Recent Advances in Open Set Recognition: A Survey](https://mlsanity.com/paper/1811.08581/) (2018)
- [C2AE: Class Conditioned Auto-Encoder for Open-set Recognition](https://mlsanity.com/paper/1904.01198/) (2019)
- [Fully Convolutional Open Set Segmentation](https://mlsanity.com/paper/2006.14673/) (2020)
- [Towards Open-Set Semantic Segmentation of Aerial Images](https://mlsanity.com/paper/2001.10063/) (2020)

## Built on by (most cited first, 3 of 3)

- [Open Scene Understanding: Grounded Situation Recognition Meets Segment Anything for Helping People with Visual Impairments](https://mlsanity.com/paper/2307.07757/) (2023)
- [Finding Outliers in a Haystack: Anomaly Detection for Large Pointcloud Scenes](https://mlsanity.com/paper/2508.17634/) (2025)
- [FuSS: Fusing Superpixels for Improved Segmentation Consistency](https://mlsanity.com/paper/2206.02714/) (2022)

## Abstract (arXiv)

Open set segmentation is a relatively new and unexploredtask, with just a handful of methods proposed to model suchtasks.We propose a novel method called CoReSeg thattackles the issue using class conditional reconstruction ofthe input images according to their pixelwise mask. Ourmethod conditions each input pixel to all known classes,expecting higher errors for pixels of unknown classes. Itwas observed that the proposed method produces better se-mantic consistency in its predictions, resulting in cleanersegmentation maps that better fit object boundaries. CoRe-Seg outperforms state-of-the-art methods on the Vaihin-gen and Potsdam ISPRS datasets, while also being com-petitive on the Houston 2018 IEEE GRSS Data Fusiondataset. Official implementation for CoReSeg is availableat:https://github.com/iannunes/CoReSeg.