🎉 TMLR2024 & ICLR2025 - Probable-class nearest neighbor explanations

Our work PCNN: Probable-Class Nearest-Neighbor Explanations Improve Fine-Grained Image Classification Accuracy for AIs and Humans got accepted at Transactions on Machine Learning Research. It was also invited to present at ICLR 2025 as representative of high-quality papers from TMLR.

We present a new class of nearest-neighbor explanations (called PCNN) and show a novel utility of the XAI method: To improve predictions of a frozen, pretrained classifier C. Our method consistently improves fine-grained image classification accuracy on CUB-200, Cars-196, and Dogs-120. Also, a human study finds that showing layusers our PCNN explanations improves their decision accuracy over showing only the top-1 class examples (as in prior work).

This is a 2-year project and there is a very interesting story behind it. Look at the Lessons page to read my story 📚.