Back to selected work
Competition2026Public repository

DCIC Scene-Text Image Forgery Analysis

A time-boxed pipeline combining a vision-language model and a segmentation network for forgery detection, localization, and attribution.

My role
System design, model adaptation, and pipeline integration
Methods & tools
Qwen-VL · QLoRA · ResNet34-UNet · Structured prompting
Image forgery workflow combining semantic VLM decisions with segmentation-based localization

Problem & challenge

A single model struggled to cover both semantic judgment and pixel-level localization, while the competition window demanded fast, independent iteration and reliable integration.

Key contributions

  1. Used a vision-language model for global decisions and structured attribution, with a segmentation network for pixel-level masks.

  2. Applied QLoRA for efficient adaptation and designed robust structured output with fallback parsing.

  3. Decoupled the two branches so they could be iterated independently under a strict delivery window.

Outcome & disclosure boundary

Delivered the full detection, localization, and explanation pipeline within the competition window, validating the engineering value of the VLM-plus-segmentation design.

  • Qwen-VL
  • QLoRA
  • ResNet34-UNet
  • Structured prompting
  • Segmentation
View on GitHub