# Label conditioned segmentation

arXiv: https://arxiv.org/abs/2203.10091 · HTML: https://mlsanity.com/paper/2203.10091/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 16 references that are in the map.
- First posted on arXiv 17 Mar 2022.

## Builds on (most cited first, 11 of 11)

- [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)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [3D MRI brain tumor segmentation using autoencoder regularization](https://mlsanity.com/paper/1810.11654/) (2018)
- [CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learning](https://mlsanity.com/paper/1903.02351/) (2019)
- [Fast-SCNN: Fast Semantic Segmentation Network](https://mlsanity.com/paper/1902.04502/) (2019)
- [Semi-supervised few-shot learning for medical image segmentation](https://mlsanity.com/paper/2003.08462/) (2020)
- [Scaling Semantic Segmentation Beyond 1K Classes on a Single GPU](https://mlsanity.com/paper/2012.07489/) (2020)
- [Ensembling Low Precision Models for Binary Biomedical Image Segmentation](https://mlsanity.com/paper/2010.08648/) (2020)
- [Multi-class Semantic Segmentation of Skin Lesions via Fully Convolutional Networks](https://mlsanity.com/paper/1711.10449/) (2017)
- [An Auto-Encoder Strategy for Adaptive Image Segmentation](https://mlsanity.com/paper/2004.13903/) (2020)

## Abstract (arXiv)

Semantic segmentation is an important task in computer vision that is often tackled with convolutional neural networks (CNNs). A CNN learns to produce pixel-level predictions through training on pairs of images and their corresponding ground-truth segmentation labels. For segmentation tasks with multiple classes, the standard approach is to use a network that computes a multi-channel probabilistic segmentation map, with each channel representing one class. In applications where the image grid size (e.g., when it is a 3D volume) and/or the number of labels is relatively large, the standard (baseline) approach can become prohibitively expensive for our computational resources. In this paper, we propose a simple yet effective method to address this challenge. In our approach, the segmentation network produces a single-channel output, while being conditioned on a single class label, which determines the output class of the network. Our method, called label conditioned segmentation (LCS), can be used to segment images with a very large number of classes, which might be infeasible for the baseline approach. We also demonstrate in the experiments that label conditioning can improve the accuracy of a given backbone architecture, likely, thanks to its parameter efficiency. Finally, as we show in our results, an LCS model can produce previously unseen fine-grained labels during inference time, when only coarse labels were available during training. We provide all of our code here: https://github.com/tym002/Label-conditioned-segmentation