# Explore the Power of Synthetic Data on Few-shot Object Detection

arXiv: https://arxiv.org/abs/2303.13221 · HTML: https://mlsanity.com/paper/2303.13221/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 48 references that are in the map.
- First posted on arXiv 23 Mar 2023.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [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)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [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)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [YOLO9000: Better, Faster, Stronger](https://mlsanity.com/paper/1612.08242/) (2016)
- [Cascaded Diffusion Models for High Fidelity Image Generation](https://mlsanity.com/paper/2106.15282/) (2021)
- [Improved Techniques for Training Score-Based Generative Models](https://mlsanity.com/paper/2006.09011/) (2020)
- [Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation](https://mlsanity.com/paper/2012.07177/) (2020)
- [Is synthetic data from generative models ready for image recognition?](https://mlsanity.com/paper/2210.07574/) (2022)
- [Frustratingly Simple Few-Shot Object Detection](https://mlsanity.com/paper/2003.06957/) (2020)
- [Few-shot Object Detection via Feature Reweighting](https://mlsanity.com/paper/1812.01866/) (2018)
- [Few-Shot Object Detection with Attention-RPN and Multi-Relation Detector](https://mlsanity.com/paper/1908.01998/) (2019)
- [Dynamic Head: Unifying Object Detection Heads with Attentions](https://mlsanity.com/paper/2106.08322/) (2021)
- [Meta R-CNN : Towards General Solver for Instance-level Few-shot Learning](https://mlsanity.com/paper/1909.13032/) (2019)
- [FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding](https://mlsanity.com/paper/2103.05950/) (2021)
- [Multi-Scale Positive Sample Refinement for Few-Shot Object Detection](https://mlsanity.com/paper/2007.09384/) (2020)
- [DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detection](https://mlsanity.com/paper/2108.09017/) (2021)
- [The Majority Can Help The Minority: Context-rich Minority Oversampling for Long-tailed Classification](https://mlsanity.com/paper/2112.00412/) (2021)
- [Beyond Max-Margin: Class Margin Equilibrium for Few-shot Object Detection](https://mlsanity.com/paper/2103.04612/) (2021)
- [Few-Shot Object Detection with Fully Cross-Transformer](https://mlsanity.com/paper/2203.15021/) (2022)
- [Meta Faster R-CNN: Towards Accurate Few-Shot Object Detection with Attentive Feature Alignment](https://mlsanity.com/paper/2104.07719/) (2021)

## Built on by (most cited first, 30 of 38)

- [Self-Consuming Generative Models Go MAD](https://mlsanity.com/paper/2307.01850/) (2023)
- [A Tale of Tails: Model Collapse as a Change of Scaling Laws](https://mlsanity.com/paper/2402.07043/) (2024)
- [Fine-tuning Multimodal LLMs to Follow Zero-shot Demonstrative Instructions](https://mlsanity.com/paper/2308.04152/) (2023)
- [Fill-Up: Balancing Long-Tailed Data with Generative Models](https://mlsanity.com/paper/2306.07200/) (2023)
- [Feedback-guided Data Synthesis for Imbalanced Classification](https://mlsanity.com/paper/2310.00158/) (2023)
- [DataDream: Few-shot Guided Dataset Generation](https://mlsanity.com/paper/2407.10910/) (2024)
- [Diversify, Don't Fine-Tune: Scaling Up Visual Recognition Training with Synthetic Images](https://mlsanity.com/paper/2312.02253/) (2023)
- [Mask Factory: Towards High-quality Synthetic Data Generation for Dichotomous Image Segmentation](https://mlsanity.com/paper/2412.19080/) (2024)
- [Domain-RAG: Retrieval-Guided Compositional Image Generation for Cross-Domain Few-Shot Object Detection](https://mlsanity.com/paper/2506.05872/) (2025)
- [AI-Generated Images as Data Source: The Dawn of Synthetic Era](https://mlsanity.com/paper/2310.01830/) (2023)
- [Interactive Data Synthesis for Systematic Vision Adaptation via LLMs-AIGCs Collaboration](https://mlsanity.com/paper/2305.12799/) (2023)
- [Data Augmentation for Image Classification using Generative AI](https://mlsanity.com/paper/2409.00547/) (2024)
- [How far can we go with ImageNet for Text-to-Image generation?](https://mlsanity.com/paper/2502.21318/) (2025)
- [Personalized Representation from Personalized Generation](https://mlsanity.com/paper/2412.16156/) (2024)
- [Control Copy-Paste: Controllable Diffusion-Based Augmentation Method for Remote Sensing Few-Shot Object Detection](https://mlsanity.com/paper/2507.21816/) (2025)
- [High-dimensional Analysis of Synthetic Data Selection](https://mlsanity.com/paper/2510.08123/) (2025)
- [Multi-Perspective Data Augmentation for Few-shot Object Detection](https://mlsanity.com/paper/2502.18195/) (2025)
- [A Unified Framework for Generative Data Augmentation: A Comprehensive Survey](https://mlsanity.com/paper/2310.00277/) (2023)
- [Auto Cherry-Picker: Learning from High-quality Generative Data Driven by Language](https://mlsanity.com/paper/2406.20085/) (2024)
- [Can Generative Models Improve Self-Supervised Representation Learning?](https://mlsanity.com/paper/2403.05966/) (2024)
- [Weak-to-Strong Compositional Learning from Generative Models for Language-based Object Detection](https://mlsanity.com/paper/2407.15296/) (2024)
- [Training-Free Synthetic Data Generation with Dual IP-Adapter Guidance](https://mlsanity.com/paper/2509.22635/) (2025)
- [Synthetic data enables context-aware bioacoustic sound event detection](https://mlsanity.com/paper/2503.00296/) (2025)
- [Lacking Data? No worries! How synthetic images can alleviate image scarcity in wildlife surveys: a case study with muskox (Ovibos moschatus)](https://mlsanity.com/paper/2511.11882/) (2025)
- [Boosting Few-Shot Detection with Large Language Models and Layout-to-Image Synthesis](https://mlsanity.com/paper/2410.06841/) (2024)
- [Sim2Real Transfer for Vision-Based Grasp Verification](https://mlsanity.com/paper/2505.03046/) (2025)
- [LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance](https://mlsanity.com/paper/2505.11703/) (2025)
- [Can We Challenge Open-Vocabulary Object Detectors with Generated Content in Street Scenes?](https://mlsanity.com/paper/2506.23751/) (2025)
- [Data-Chain Backdoor: Do You Trust Diffusion Models as Generative Data Supplier?](https://mlsanity.com/paper/2512.15769/) (2025)
- [When Sample Selection Bias Precipitates Model Collapse](https://mlsanity.com/paper/2606.13732/) (2026)

## Abstract (arXiv)

Few-shot object detection (FSOD) aims to expand an object detector for novel categories given only a few instances for training. The few training samples restrict the performance of FSOD model. Recent text-to-image generation models have shown promising results in generating high-quality images. How applicable these synthetic images are for FSOD tasks remains under-explored. This work extensively studies how synthetic images generated from state-of-the-art text-to-image generators benefit FSOD tasks. We focus on two perspectives: (1) How to use synthetic data for FSOD? (2) How to find representative samples from the large-scale synthetic dataset? We design a copy-paste-based pipeline for using synthetic data. Specifically, saliency object detection is applied to the original generated image, and the minimum enclosing box is used for cropping the main object based on the saliency map. After that, the cropped object is randomly pasted on the image, which comes from the base dataset. We also study the influence of the input text of text-to-image generator and the number of synthetic images used. To construct a representative synthetic training dataset, we maximize the diversity of the selected images via a sample-based and cluster-based method. However, the severe problem of high false positives (FP) ratio of novel categories in FSOD can not be solved by using synthetic data. We propose integrating CLIP, a zero-shot recognition model, into the FSOD pipeline, which can filter 90% of FP by defining a threshold for the similarity score between the detected object and the text of the predicted category. Extensive experiments on PASCAL VOC and MS COCO validate the effectiveness of our method, in which performance gain is up to 21.9% compared to the few-shot baseline.