# Free-Lunch Augmentation by Revisiting Diffusion-Based Data Generation for Cross-Domain Few-Shot Object Detection

arXiv: https://arxiv.org/abs/2608.04394 · HTML: https://mlsanity.com/paper/2608.04394/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models.
- Builds on 45 of its 54 references that are in the map.
- First posted on arXiv 5 Aug 2026.

## 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 45)

- [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)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations](https://mlsanity.com/paper/2108.01073/) (2021)
- [IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2308.06721/) (2023)
- [Grounded Language-Image Pre-training](https://mlsanity.com/paper/2112.03857/) (2021)
- [Exploring Plain Vision Transformer Backbones for Object Detection](https://mlsanity.com/paper/2203.16527/) (2022)
- [Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation](https://mlsanity.com/paper/2012.07177/) (2020)
- [Understanding Diffusion Models: A Unified Perspective](https://mlsanity.com/paper/2208.11970/) (2022)
- [Is synthetic data from generative models ready for image recognition?](https://mlsanity.com/paper/2210.07574/) (2022)
- [Effective Data Augmentation With Diffusion Models](https://mlsanity.com/paper/2302.07944/) (2023)
- [Personalize Segment Anything Model with One Shot](https://mlsanity.com/paper/2305.03048/) (2023)
- [A Survey on Generative Diffusion Model](https://mlsanity.com/paper/2209.02646/) (2022)
- [Generative Diffusion Prior for Unified Image Restoration and Enhancement](https://mlsanity.com/paper/2304.01247/) (2023)
- [Hypercorrelation Squeeze for Few-Shot Segmentation](https://mlsanity.com/paper/2104.01538/) (2021)
- [Prompt, Generate, then Cache: Cascade of Foundation Models makes Strong Few-shot Learners](https://mlsanity.com/paper/2303.02151/) (2023)
- [Few-Shot Segmentation Without Meta-Learning: A Good Transductive Inference Is All You Need?](https://mlsanity.com/paper/2012.06166/) (2020)
- [Entropy Maximization and Meta Classification for Out-Of-Distribution Detection in Semantic Segmentation](https://mlsanity.com/paper/2012.06575/) (2020)
- [Self-Support Few-Shot Semantic Segmentation](https://mlsanity.com/paper/2207.11549/) (2022)
- [Reliability of CKA as a Similarity Measure in Deep Learning](https://mlsanity.com/paper/2210.16156/) (2022)
- [CLIP for All Things Zero-Shot Sketch-Based Image Retrieval, Fine-Grained or Not](https://mlsanity.com/paper/2303.13440/) (2023)
- [DiffuseMix: Label-Preserving Data Augmentation with Diffusion Models](https://mlsanity.com/paper/2405.14881/) (2024)
- [Residual Denoising Diffusion Models](https://mlsanity.com/paper/2308.13712/) (2023)
- [Feature-Proxy Transformer for Few-Shot Segmentation](https://mlsanity.com/paper/2210.06908/) (2022)
- [Cross-Domain Few-Shot Object Detection via Enhanced Open-Set Object Detector](https://mlsanity.com/paper/2402.03094/) (2024)
- [Flatten Long-Range Loss Landscapes for Cross-Domain Few-Shot Learning](https://mlsanity.com/paper/2403.00567/) (2024)
- [APSeg: Auto-Prompt Network for Cross-Domain Few-Shot Semantic Segmentation](https://mlsanity.com/paper/2406.08372/) (2024)
- [AI-Generated Content (AIGC) for Various Data Modalities: A Survey](https://mlsanity.com/paper/2308.14177/) (2023)

## Abstract (arXiv)

Cross-Domain Few-Shot Object Detection (CDFSOD) aims to transfer knowledge from data-rich upstream generic domains to downstream expert domains using scarce training data, where the significant domain gap and data scarcity make it an unsolved challenge. To address this problem, we revisit a natural yet underexplored approach in CDFSOD: data augmentation, by directly synthesizing data through diffusion models to supplement limited training samples. However, due to large domain gaps, we find that current diffusion methods cannot produce good results, leading to performance even lower than using the original images. To address these limitations, we divide the domain gaps into visual gaps and semantic gaps for separate analysis. For the visual gap, we find that the diffusion model cannot distinguish noise from useful information on expert domains, which can be mitigated by adding weakened noise. For the semantic gap, we find that the background semantics shows much smaller gaps between domains than foreground semantics, and we can bridge this gap by background inpainting. Based on the above analysis, we propose a method (Selective Inpainting with Tailored Noise, SITN) to dynamically take different strategies for downstream data synthesis based on their different gaps from the general domain, including a Generation Module for adding tailored noise and a Selection Module to dynamically select the inpainting regions. Extensive experiments on 6 datasets of CDFSOD and 4 datasets of cross-domain few-shot segmentation (CDFSS) validate that we can synthesize helpful data, achieving new state-of-the-art performance. Our codes is available at https://github.com/zzzzj311-droid/Free-Lunch-SITN