# Zero-shot Synthesis with Group-Supervised Learning

arXiv: https://arxiv.org/abs/2009.06586 · HTML: https://mlsanity.com/paper/2009.06586/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Sep 2020.

## Built on by (most cited first, 17 of 17)

- [Neural-Sim: Learning to Generate Training Data with NeRF](https://mlsanity.com/paper/2207.11368/) (2022)
- [Enhance Image-to-Image Generation with LLaVA-generated Prompts](https://mlsanity.com/paper/2406.01956/) (2024)
- [DALL-E for Detection: Language-driven Compositional Image Synthesis for Object Detection](https://mlsanity.com/paper/2206.09592/) (2022)
- [Contributions of Shape, Texture, and Color in Visual Recognition](https://mlsanity.com/paper/2207.09510/) (2022)
- [Beyond Generation: Harnessing Text to Image Models for Object Detection and Segmentation](https://mlsanity.com/paper/2309.05956/) (2023)
- [Graph-based Unsupervised Disentangled Representation Learning via Multimodal Large Language Models](https://mlsanity.com/paper/2407.18999/) (2024)
- [Multi-Modal UAV Detection, Classification and Tracking Algorithm -- Technical Report for CVPR 2024 UG2 Challenge](https://mlsanity.com/paper/2405.16464/) (2024)
- [Generative Artificial Intelligence Meets Synthetic Aperture Radar: A Survey](https://mlsanity.com/paper/2411.05027/) (2024)
- [Encouraging Disentangled and Convex Representation with Controllable Interpolation Regularization](https://mlsanity.com/paper/2112.03163/) (2021)
- [Distortion-Disentangled Contrastive Learning](https://mlsanity.com/paper/2303.05066/) (2023)
- [DiffuseGAE: Controllable and High-fidelity Image Manipulation from Disentangled Representation](https://mlsanity.com/paper/2307.05899/) (2023)
- [Causal Disentanglement for Robust Long-tail Medical Image Generation](https://mlsanity.com/paper/2504.14450/) (2025)
- [Weakly Supervised Disentangled Representation for Goal-conditioned Reinforcement Learning](https://mlsanity.com/paper/2202.13624/) (2022)
- [An Identity-Preserved Framework for Human Motion Transfer](https://mlsanity.com/paper/2204.06862/) (2022)
- [Break The Spell Of Total Correlation In betaTCVAE](https://mlsanity.com/paper/2210.08794/) (2022)
- [RAGE for the Machine: Image Compression with Low-Cost Random Access for Embedded Applications](https://mlsanity.com/paper/2402.05974/) (2024)
- [Disentangling Representation using Attributes-based Gaussian Estimation for Medical Sound Diagnosis](https://mlsanity.com/paper/2608.29026/) (2026)

## Abstract (arXiv)

Visual cognition of primates is superior to that of artificial neural networks in its ability to 'envision' a visual object, even a newly-introduced one, in different attributes including pose, position, color, texture, etc. To aid neural networks to envision objects with different attributes, we propose a family of objective functions, expressed on groups of examples, as a novel learning framework that we term Group-Supervised Learning (GSL). GSL allows us to decompose inputs into a disentangled representation with swappable components, that can be recombined to synthesize new samples. For instance, images of red boats & blue cars can be decomposed and recombined to synthesize novel images of red cars. We propose an implementation based on auto-encoder, termed group-supervised zero-shot synthesis network (GZS-Net) trained with our learning framework, that can produce a high-quality red car even if no such example is witnessed during training. We test our model and learning framework on existing benchmarks, in addition to anew dataset that we open-source. We qualitatively and quantitatively demonstrate that GZS-Net trained with GSL outperforms state-of-the-art methods.