# GANORCON: Are Generative Models Useful for Few-shot Segmentation?

arXiv: https://arxiv.org/abs/2112.00854 · HTML: https://mlsanity.com/paper/2112.00854/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 45 references that are in the map.
- First posted on arXiv 1 Dec 2021.

## Builds on (most cited first, 30 of 34)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination](https://mlsanity.com/paper/1805.01978/) (2018)
- [Unsupervised Representation Learning by Predicting Image Rotations](https://mlsanity.com/paper/1803.07728/) (2018)
- [Context Encoders: Feature Learning by Inpainting](https://mlsanity.com/paper/1604.07379/) (2016)
- [Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles](https://mlsanity.com/paper/1603.09246/) (2016)
- [Big Self-Supervised Models are Strong Semi-Supervised Learners](https://mlsanity.com/paper/2006.10029/) (2020)
- [LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop](https://mlsanity.com/paper/1506.03365/) (2015)
- [Contrastive Multiview Coding](https://mlsanity.com/paper/1906.05849/) (2019)
- [Learning deep representations by mutual information estimation and maximization](https://mlsanity.com/paper/1808.06670/) (2018)
- [Colorful Image Colorization](https://mlsanity.com/paper/1603.08511/) (2016)
- [Learning Representations by Maximizing Mutual Information Across Views](https://mlsanity.com/paper/1906.00910/) (2019)
- [Dense Contrastive Learning for Self-Supervised Visual Pre-Training](https://mlsanity.com/paper/2011.09157/) (2020)
- [Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networks](https://mlsanity.com/paper/1406.6909/) (2014)
- [DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effort](https://mlsanity.com/paper/2104.06490/) (2021)
- [Semi-Supervised Semantic Segmentation with High- and Low-level Consistency](https://mlsanity.com/paper/1908.05724/) (2019)
- [Unsupervised Learning of Dense Visual Representations](https://mlsanity.com/paper/2011.05499/) (2020)
- [Hypercolumns for Object Segmentation and Fine-grained Localization](https://mlsanity.com/paper/1411.5752/) (2014)
- [Generative Models as a Data Source for Multiview Representation Learning](https://mlsanity.com/paper/2106.05258/) (2021)

## Built on by (most cited first, 13 of 13)

- [SemMAE: Semantic-Guided Masking for Learning Masked Autoencoders](https://mlsanity.com/paper/2206.10207/) (2022)
- [Leaving Reality to Imagination: Robust Classification via Generated Datasets](https://mlsanity.com/paper/2302.02503/) (2023)
- [Improving Few-Shot Part Segmentation using Coarse Supervision](https://mlsanity.com/paper/2204.05393/) (2022)
- [ZeroDiff: Solidified Visual-Semantic Correlation in Zero-Shot Learning](https://mlsanity.com/paper/2406.02929/) (2024)
- [The Art of Camouflage: Few-Shot Learning for Animal Detection and Segmentation](https://mlsanity.com/paper/2304.07444/) (2023)
- [PARTICLE: Part Discovery and Contrastive Learning for Fine-grained Recognition](https://mlsanity.com/paper/2309.13822/) (2023)
- [Leveraging GAN Priors for Few-Shot Part Segmentation](https://mlsanity.com/paper/2207.13428/) (2022)
- [One-Shot Synthesis of Images and Segmentation Masks](https://mlsanity.com/paper/2209.07547/) (2022)
- [PartSeg: Few-shot Part Segmentation via Part-aware Prompt Learning](https://mlsanity.com/paper/2308.12757/) (2023)
- [CycleSAM: Few-Shot Surgical Scene Segmentation with Cycle- and Scene-Consistent Feature Matching](https://mlsanity.com/paper/2407.06795/) (2024)
- [Accidental Turntables: Learning 3D Pose by Watching Objects Turn](https://mlsanity.com/paper/2212.06300/) (2022)
- [Tiny models from tiny data: Textual and null-text inversion for few-shot distillation](https://mlsanity.com/paper/2406.03146/) (2024)
- [Deep ContourFlow: Advancing Active Contours with Deep Learning](https://mlsanity.com/paper/2407.10696/) (2024)

## Abstract (arXiv)

Advances in generative modeling based on GANs has motivated the community to find their use beyond image generation and editing tasks. In particular, several recent works have shown that GAN representations can be re-purposed for discriminative tasks such as part segmentation, especially when training data is limited. But how do these improvements stack-up against recent advances in self-supervised learning? Motivated by this we present an alternative approach based on contrastive learning and compare their performance on standard few-shot part segmentation benchmarks. Our experiments reveal that not only do the GAN-based approach offer no significant performance advantage, their multi-step training is complex, nearly an order-of-magnitude slower, and can introduce additional bias. These experiments suggest that the inductive biases of generative models, such as their ability to disentangle shape and texture, are well captured by standard feed-forward networks trained using contrastive learning. These experiments suggest that the inductive biases present in current generative models, such as their ability to disentangle shape and texture, are well captured by standard feed-forward networks trained using contrastive learning.