# SCoFT: Self-Contrastive Fine-Tuning for Equitable Image Generation

arXiv: https://arxiv.org/abs/2401.08053 · HTML: https://mlsanity.com/paper/2401.08053/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 64 references that are in the map.
- First posted on arXiv 16 Jan 2024.

## Builds on (most cited first, 30 of 43)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [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)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs](https://mlsanity.com/paper/2111.02114/) (2021)
- [Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer](https://mlsanity.com/paper/1907.01341/) (2019)
- [Demystifying MMD GANs](https://mlsanity.com/paper/1801.01401/) (2018)
- [Multi-Concept Customization of Text-to-Image Diffusion](https://mlsanity.com/paper/2212.04488/) (2022)
- [DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulation](https://mlsanity.com/paper/2110.02711/) (2021)
- [Directly Fine-Tuning Diffusion Models on Differentiable Rewards](https://mlsanity.com/paper/2309.17400/) (2023)
- [Blended Latent Diffusion](https://mlsanity.com/paper/2206.02779/) (2022)
- [Unified Concept Editing in Diffusion Models](https://mlsanity.com/paper/2308.14761/) (2023)
- [AI and the Everything in the Whole Wide World Benchmark](https://mlsanity.com/paper/2111.15366/) (2021)
- [Multimodal datasets: misogyny, pornography, and malignant stereotypes](https://mlsanity.com/paper/2110.01963/) (2021)
- [Ablating Concepts in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2303.13516/) (2023)
- [WIT: Wikipedia-based Image Text Dataset for Multimodal Multilingual Machine Learning](https://mlsanity.com/paper/2103.01913/) (2021)
- [Stable Bias: Analyzing Societal Representations in Diffusion Models](https://mlsanity.com/paper/2303.11408/) (2023)
- [A Framework for Understanding Sources of Harm throughout the Machine Learning Life Cycle](https://mlsanity.com/paper/1901.10002/) (2019)
- [Visually Grounded Reasoning across Languages and Cultures](https://mlsanity.com/paper/2109.13238/) (2021)
- [RedCaps: web-curated image-text data created by the people, for the people](https://mlsanity.com/paper/2111.11431/) (2021)
- [MiDaS v3.1 -- A Model Zoo for Robust Monocular Relative Depth Estimation](https://mlsanity.com/paper/2307.14460/) (2023)
- [Concept Sliders: LoRA Adaptors for Precise Control in Diffusion Models](https://mlsanity.com/paper/2311.12092/) (2023)
- [Towards Accountability for Machine Learning Datasets: Practices from Software Engineering and Infrastructure](https://mlsanity.com/paper/2010.13561/) (2020)
- [ERNIE-ViLG 2.0: Improving Text-to-Image Diffusion Model with Knowledge-Enhanced Mixture-of-Denoising-Experts](https://mlsanity.com/paper/2210.15257/) (2022)

## Built on by (most cited first, 19 of 19)

- [Survey of Bias In Text-to-Image Generation: Definition, Evaluation, and Mitigation](https://mlsanity.com/paper/2404.01030/) (2024)
- [Beyond Aesthetics: Cultural Competence in Text-to-Image Models](https://mlsanity.com/paper/2407.06863/) (2024)
- [Efficient Diffusion Transformer with Step-wise Dynamic Attention Mediators](https://mlsanity.com/paper/2408.05710/) (2024)
- [SANER: Annotation-free Societal Attribute Neutralizer for Debiasing CLIP](https://mlsanity.com/paper/2408.10202/) (2024)
- [CulturalFrames: Assessing Cultural Expectation Alignment in Text-to-Image Models and Evaluation Metrics](https://mlsanity.com/paper/2506.08835/) (2025)
- [Fairness and Bias Mitigation in Computer Vision: A Survey](https://mlsanity.com/paper/2408.02464/) (2024)
- [Where Culture Fades: Revealing the Cultural Gap in Text-to-Image Generation](https://mlsanity.com/paper/2511.17282/) (2025)
- [Culture in Action: Evaluating Text-to-Image Models through Social Activities](https://mlsanity.com/paper/2511.05681/) (2025)
- [Culture-TRIP: Culturally-Aware Text-to-Image Generation with Iterative Prompt Refinement](https://mlsanity.com/paper/2502.16902/) (2025)
- [Can we Debias Social Stereotypes in AI-Generated Images? Examining Text-to-Image Outputs and User Perceptions](https://mlsanity.com/paper/2505.20692/) (2025)
- [Bias in Gender Bias Benchmarks: How Spurious Features Distort Evaluation](https://mlsanity.com/paper/2509.07596/) (2025)
- [FairSkin: Fair Diffusion for Skin Disease Image Generation](https://mlsanity.com/paper/2410.22551/) (2024)
- [Exposing Blindspots: Cultural Bias Evaluation in Generative Image Models](https://mlsanity.com/paper/2510.20042/) (2025)
- [Linear Differential Vision Transformer: Learning Visual Contrasts via Pairwise Differentials](https://mlsanity.com/paper/2511.00833/) (2025)
- [Toward Trustworthy Portrait Editing: Evaluation of Demographic Misrepresentation in I2I Models](https://mlsanity.com/paper/2602.16149/) (2026)
- [TokenDial: Continuous Attribute Control for Text-to-Video Generation in Visual Dial Space](https://mlsanity.com/paper/2603.27520/) (2026)
- [Training-Free Debiasing of Diffusion Models via CLIP-Guided Denoising Optimization](https://mlsanity.com/paper/2607.00817/) (2026)
- [Beyond Sliders: Mastering the Art of Diffusion-based Image Manipulation](https://mlsanity.com/paper/2509.11213/) (2025)
- [KG-FairDiff: Knowledge Graph-Guided Prompt Refinement for Demographically Fair Text-to-Image Generation](https://mlsanity.com/paper/2606.01282/) (2026)

## Abstract (arXiv)

Accurate representation in media is known to improve the well-being of the people who consume it. Generative image models trained on large web-crawled datasets such as LAION are known to produce images with harmful stereotypes and misrepresentations of cultures. We improve inclusive representation in generated images by (1) engaging with communities to collect a culturally representative dataset that we call the Cross-Cultural Understanding Benchmark (CCUB) and (2) proposing a novel Self-Contrastive Fine-Tuning (SCoFT) method that leverages the model's known biases to self-improve. SCoFT is designed to prevent overfitting on small datasets, encode only high-level information from the data, and shift the generated distribution away from misrepresentations encoded in a pretrained model. Our user study conducted on 51 participants from 5 different countries based on their self-selected national cultural affiliation shows that fine-tuning on CCUB consistently generates images with higher cultural relevance and fewer stereotypes when compared to the Stable Diffusion baseline, which is further improved with our SCoFT technique.