Skip to content
Quantoros

Your text-to-image system generates biased images. How do you address it?

Computer VisionLevel: IntermediateTroubleshooting Scenarios

Your text-to-image system generates biased images. How do you address it?

Hints
  • Identify the prediction unit: image, object, pixel or sequence.
  • How do occlusion, lighting or domain changes affect results and evaluation?

Answer

  1. Bias audit: systematically test prompts like "a photo of a doctor" / "a photo of a nurse" across demographic variations. Measure demographic distribution of generated images.
  2. Prompt modification: add diversity guidance to default prompts — "diverse group of people," "various ethnicities and genders"
  3. CLIP-based filter + regeneration: use CLIP to check if generated image matches stereotyped representations; regenerate if bias threshold exceeded
  4. Fine-tuning on balanced data: fine-tune the model (LoRA + DreamBooth) on a balanced, curated dataset with diverse representation
  5. User controls: let users specify demographic attributes they want represented rather than relying on model defaults

Source and licence: JustInCache & contributors — Awesome AI Interviews · Apache-2.0

Related questions