# Are They the Same Picture? Adapting Concept Bottleneck Models for Human-AI Collaboration in Image Retrieval

**IJCAI 2024** (Human-Centered AI track)

*Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, IJCAI-24*

**Vaibhav Balloli**, Sara Beery, Elizabeth Bondi-Kelly

Distinctions: <5% accept

## Summary

CHAIR adapts Concept Bottleneck Models so experts can intervene on intermediate concepts during image retrieval, a setting that matters for wildlife re-identification platforms like ElephantBook. Flexible levels of intervention let domain experts spend effort where it's most useful, achieving genuine human-AI complementarity.

## Identifiers

- DOI: [10.24963/ijcai.2024/866](https://doi.org/10.24963/ijcai.2024/866)
- PDF: https://www.ijcai.org/proceedings/2024/0866.pdf

## Links

- PDF: https://www.ijcai.org/proceedings/2024/0866.pdf
- Proceedings: https://doi.org/10.24963/ijcai.2024/866
- Project: https://realize-lab.github.io/CHAIR
- Code: https://github.com/realize-lab/CHAIR

## Topics

vision, social-impact

## Citation

```bibtex
@inproceedings{balloli2024chair,
  title     = {Are They the Same Picture? Adapting Concept Bottleneck Models for Human-AI Collaboration in Image Retrieval},
  author    = {Balloli, Vaibhav and Beery, Sara and Bondi-Kelly, Elizabeth},
  booktitle = {Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, {IJCAI-24}},
  editor    = {Kate Larson},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  pages     = {7824--7832},
  year      = {2024},
  month     = {8},
  note      = {Human-Centred AI},
  doi       = {10.24963/ijcai.2024/866},
  url       = {https://doi.org/10.24963/ijcai.2024/866}
}
```

---

Canonical HTML page: https://profile.vballoli.com/papers/chair/