# Semantic Generative Augmentations for Few-Shot Counting

arXiv: https://arxiv.org/abs/2311.16122 · HTML: https://mlsanity.com/paper/2311.16122/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models.
- Builds on 37 of its 45 references that are in the map.
- First posted on arXiv 26 Oct 2023.

## Placed in

- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)

## Builds on (most cited first, 30 of 37)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.08453/) (2023)
- [Aligning Text-to-Image Models using Human Feedback](https://mlsanity.com/paper/2302.12192/) (2023)
- [Synthetic Data from Diffusion Models Improves ImageNet Classification](https://mlsanity.com/paper/2304.08466/) (2023)
- [Is synthetic data from generative models ready for image recognition?](https://mlsanity.com/paper/2210.07574/) (2022)
- [Composer: Creative and Controllable Image Synthesis with Composable Conditions](https://mlsanity.com/paper/2302.09778/) (2023)
- [Effective Data Augmentation With Diffusion Models](https://mlsanity.com/paper/2302.07944/) (2023)
- [Data Augmentation Generative Adversarial Networks](https://mlsanity.com/paper/1711.04340/) (2017)
- [DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effort](https://mlsanity.com/paper/2104.06490/) (2021)
- [Teaching CLIP to Count to Ten](https://mlsanity.com/paper/2302.12066/) (2023)
- [StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learners](https://mlsanity.com/paper/2306.00984/) (2023)
- [Fake it till you make it: Learning transferable representations from synthetic ImageNet clones](https://mlsanity.com/paper/2212.08420/) (2022)
- [Grounded Text-to-Image Synthesis with Attention Refocusing](https://mlsanity.com/paper/2306.05427/) (2023)
- [Drone-based Object Counting by Spatially Regularized Regional Proposal Network](https://mlsanity.com/paper/1707.05972/) (2017)
- [Learning To Count Everything](https://mlsanity.com/paper/2104.08391/) (2021)
- [Learning from Synthetic Data for Crowd Counting in the Wild](https://mlsanity.com/paper/1903.03303/) (2019)
- [Generative Models as a Data Source for Multiview Representation Learning](https://mlsanity.com/paper/2106.05258/) (2021)
- [Leaving Reality to Imagination: Robust Classification via Generated Datasets](https://mlsanity.com/paper/2302.02503/) (2023)
- [Class-Agnostic Counting](https://mlsanity.com/paper/1811.00472/) (2018)
- [Diversity is Definitely Needed: Improving Model-Agnostic Zero-shot Classification via Stable Diffusion](https://mlsanity.com/paper/2302.03298/) (2023)

## Built on by (most cited first, 6 of 6)

- [A Survey on Data Augmentation in Large Model Era](https://mlsanity.com/paper/2401.15422/) (2024)
- [A Survey of Data Synthesis Approaches](https://mlsanity.com/paper/2407.03672/) (2024)
- [A Survey on Class-Agnostic Counting: Advancements from Reference-Based to Open-World Text-Guided Approaches](https://mlsanity.com/paper/2501.19184/) (2025)
- [Learning from Exemplars for Interactive Image Segmentation](https://mlsanity.com/paper/2406.11472/) (2024)
- [Does it Really Count? Assessing Semantic Grounding in Text-Guided Class-Agnostic Counting](https://mlsanity.com/paper/2605.02752/) (2026)
- [One-Shot Crowd Counting With Density Guidance For Scene Adaptation](https://mlsanity.com/paper/2602.07955/) (2026)

## Abstract (arXiv)

With the availability of powerful text-to-image diffusion models, recent works have explored the use of synthetic data to improve image classification performances. These works show that it can effectively augment or even replace real data. In this work, we investigate how synthetic data can benefit few-shot class-agnostic counting. This requires to generate images that correspond to a given input number of objects. However, text-to-image models struggle to grasp the notion of count. We propose to rely on a double conditioning of Stable Diffusion with both a prompt and a density map in order to augment a training dataset for few-shot counting. Due to the small dataset size, the fine-tuned model tends to generate images close to the training images. We propose to enhance the diversity of synthesized images by exchanging captions between images thus creating unseen configurations of object types and spatial layout. Our experiments show that our diversified generation strategy significantly improves the counting accuracy of two recent and performing few-shot counting models on FSC147 and CARPK.