Prototype-Part Interpretable Image Recognition

02 — Approach

Method

The workflow below is a visual summary of the documented implementation; it is not a claim of additional system components.

1. 01

   Fine-tuned DINO with a custom part-attention module to discover meaningful object parts using only image-level labels, requiring no part annotations

   →
2. 02

   Developed a prototype-based classification framework where prototypes are actual image regions rather than abstract latent vectors, making model decisions directly human-interpretable

   →
3. 03

   Analyzed part-attention embeddings via clustering to validate semantic consistency of discovered parts and explored clustering-based explanations as a lightweight alternative to prototype matching

03 — Contribution

Contribution

• 01

  Fine-tuned DINO with a custom part-attention module to discover meaningful object parts using only image-level labels, requiring no part annotations

• 02

  Developed a prototype-based classification framework where prototypes are actual image regions rather than abstract latent vectors, making model decisions directly human-interpretable

• 03

  Analyzed part-attention embeddings via clustering to validate semantic consistency of discovered parts and explored clustering-based explanations as a lightweight alternative to prototype matching

04 — Evidence

Results

This project record verifies the delivered implementation, but does not report a comparable performance metric.