# Approximate Size Targets Are Sufficient for Accurate Semantic Segmentation

arXiv: https://arxiv.org/abs/2503.06954 · HTML: https://mlsanity.com/paper/2503.06954/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 33 references that are in the map.
- First posted on arXiv 10 Mar 2025.

## Builds on (most cited first, 23 of 23)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [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)
- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [Deep Clustering for Unsupervised Learning of Visual Features](https://mlsanity.com/paper/1807.05520/) (2018)
- [Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs](https://mlsanity.com/paper/1412.7062/) (2014)
- [Invariant Information Clustering for Unsupervised Image Classification and Segmentation](https://mlsanity.com/paper/1807.06653/) (2018)
- [ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1604.05144/) (2016)
- [Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/1803.10464/) (2018)
- [Seed, Expand and Constrain: Three Principles for Weakly-Supervised Image Segmentation](https://mlsanity.com/paper/1603.06098/) (2016)
- [Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentation](https://mlsanity.com/paper/1502.02734/) (2015)
- [Wider or Deeper: Revisiting the ResNet Model for Visual Recognition](https://mlsanity.com/paper/1611.10080/) (2016)
- [Single-Stage Semantic Segmentation from Image Labels](https://mlsanity.com/paper/2005.08104/) (2020)
- [PiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in Clustering](https://mlsanity.com/paper/2103.17070/) (2021)
- [On Regularized Losses for Weakly-supervised CNN Segmentation](https://mlsanity.com/paper/1803.09569/) (2018)
- [Learning Affinity from Attention: End-to-End Weakly-Supervised Semantic Segmentation with Transformers](https://mlsanity.com/paper/2203.02664/) (2022)
- [Constrained Convolutional Neural Networks for Weakly Supervised Segmentation](https://mlsanity.com/paper/1506.03648/) (2015)
- [SegSort: Segmentation by Discriminative Sorting of Segments](https://mlsanity.com/paper/1910.06962/) (2019)
- [Weakly Supervised Semantic Segmentation by Pixel-to-Prototype Contrast](https://mlsanity.com/paper/2110.07110/) (2021)
- [Regional Semantic Contrast and Aggregation for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2203.09653/) (2022)
- [Deep clustering: On the link between discriminative models and K-means](https://mlsanity.com/paper/1810.04246/) (2018)
- [Fluid Annotation: A Human-Machine Collaboration Interface for Full Image Annotation](https://mlsanity.com/paper/1806.07527/) (2018)

## Abstract (arXiv)

This paper demonstrates a surprising result for segmentation with image-level targets: extending binary class tags to approximate relative object-size distributions allows off-the-shelf architectures to solve the segmentation problem. A straightforward zero-avoiding KL-divergence loss for average predictions produces segmentation accuracy comparable to the standard pixel-precise supervision with full ground truth masks. In contrast, current results based on class tags typically require complex non-reproducible architectural modifications and specialized multi-stage training procedures. Our ideas are validated on PASCAL VOC using our new human annotations of approximate object sizes. We also show the results on COCO and medical data using synthetically corrupted size targets. All standard networks demonstrate robustness to the size targets' errors. For some classes, the validation accuracy is significantly better than the pixel-level supervision; the latter is not robust to errors in the masks. Our work provides new ideas and insights on image-level supervision in segmentation and may encourage other simple general solutions to the problem.